CN106203472A - A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes - Google Patents
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes Download PDFInfo
- Publication number
- CN106203472A CN106203472A CN201610483014.2A CN201610483014A CN106203472A CN 106203472 A CN106203472 A CN 106203472A CN 201610483014 A CN201610483014 A CN 201610483014A CN 106203472 A CN106203472 A CN 106203472A
- Authority
- CN
- China
- Prior art keywords
- image
- mixed attributes
- attribute
- test image
- low
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of zero sample image sorting technique based on mixed attributes direct attribute forecast model.First, training image low-level image feature is carried out sparse coding and utilizes the non-semantic attribute that obtains of coding to assist semantic attribute;Then, non-semantic attribute is constituted mixed attributes the attribute intermediate layer as direct attribute forecast model with semantic attribute, utilizes the thought of direct attribute forecast model to carry out the training of mixed attributes grader;Finally, according to the relation between mixed attributes and attribute and the classification of prediction, the prediction of test sample class label is carried out.The classification that the invention enables attribute similarity originally is more prone to be distinguished, thus improves the discrimination of zero sample image classification.
Description
Technical field
The present invention relates to a kind of method utilizing mixed attributes direct attribute forecast model to realize zero sample image classification,
Belong to zero sample image classification field.
Background technology
The semantic attribute utilizing image realizes the study hotspot that zero sample image classification is current attribute application, with biography
The image classification problem of system is different, and zero sample image is sorted in the sample that test phase classifies and identify and has neither part nor lot in grader mould
The training of type.In zero sample image classification problem, in order to realize being clipped to have no the knowledge migration of classification from visible class, mould of classifying
Type is accomplished by building a bridge from low-level image feature to class label by semantic attribute.Nearest research work proposes
A lot of image classification methods based on semantic attribute, that representative is direct attribute forecast model (Direct
Attribute Prediction, DAP) and proxy attribute forecast model (Indirect Attribute Prediction,
IAP).In zero sample image sorting technique based on semantic attribute, semantic attribute considers whether sample has a certain kind
Property, may determine that the sample position in attribute space according to " having ", the "None" of attribute, and then determine the class label of sample.But
It is that, for the classification much like to those semantic attributes (attribute space is positioned proximate to), semantic attribute is difficult to carry out them
Distinguish.
Summary of the invention
Goal of the invention: in order to overcome the deficiencies in the prior art, the present invention provides a kind of direct based on mixed attributes
Zero sample image sorting technique of forecast model, it is possible to the classification making semantic attribute similar is easily distinguished.
Technical scheme: for achieving the above object, the technical solution used in the present invention is:
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, comprises the steps:
Step 1, is learnt by sparse coding algorithm with training image low-level image feature collection, obtains base vector set;
Step 2, linearly weighs training image low-level image feature collection and test image low-level image feature collection with base vector set
Structure, obtains non-semantic property set, carries out supplementing and extending to semantic attribute collection, and then structure mixed attributes collection;
Step 3, utilizes training image low-level image feature to integrate each mixed attributes concentrated as mixed attributes and trains one to mix
Close attributive classification device;
Step 4, utilizes mixed attributes grader to be predicted test image blend attribute, obtains testing image blend and belongs to
Property prediction probability, attribute corresponding to maximum predicted probit is the test image blend attribute that prediction obtains;
Step 5, the class label of test image is predicted by the test image blend attribute utilizing prediction to obtain, and obtains
Posterior probability estimation from test image low-level image feature to test image category label;
Step 6, finds out the class label maximum so that posterior probability estimation, and category label is distributed to test figure
Picture, thus obtains testing image category label.
As the preferred version of the present invention, in described step 1, given training image low-level image feature collection X={x1,x2,...,
xΚ}∈Rd×K, wherein K is the classification number of training image, xi, i=1,2 ..., K is the i-th class training image low-level image feature, and d is
The dimension of image low-level image feature, Rd×KRepresentation dimension is the space of d × K;WithRepresent base vector set, wherein
N represents the number of base vector,J=1,2 ..., N represents jth base vector;Sparse coding Algorithm Learning is then utilized to obtain base
The method of vector set Φ is specific as follows:
Step 1.1, random initializtion base vector set Φ;
Step 1.2, substitutes into training image low-level image feature collection X in following constraint equation:
In formula, bi,j, i=1,2 ..., K;J=1,2 ..., N is activation amount, represents the i-th class training image low-level image feature
xiJth sparse coding;λ represents weight attenuation quotient;Represent sparse regular terms;Represent L1Norm, c represents one
Individual constant, is used for limiting sparse degree;
Step 1.3, first fixing initialization base vector set Φ, solve the activation that constraint equation (1) can be made to minimize
Amount bi,j;Then activation amount b is fixedi,j, solve the base vector set Φ that constraint equation (1) can be made to minimize;
Step 1.4, constantly repeats step 1.3 until convergence, tries to achieve one group of base vector set representing image low-level image feature
As the preferred version of the present invention, in described step 2, given test image set low-level image feature collection X '={ x '1,x
′2,...,x′Z}∈Rd×Z, wherein Z is the classification number of test image, x 'i, i=1,2 ..., Z is the i-th class testing image bottom
Feature, d is the dimension of image low-level image feature, Rd×ZRepresentation dimension is the space of d × Z;The basal orientation quantity set obtained is learnt by step 1
CloseTraining image low-level image feature collection X and test image low-level image feature collection X ' is carried out linear reconstruction, obtainsI=1,2 ..., K andI=1,2 ..., Z;Obtain non-semantic according to linear reconstruction result
The method of property set B is:
Adjust activation amount bi,jMake formula (2) minimum, the set B={B finally given1,B2,...,BN{ 0,1} is i.e. ∈
Training image and the non-semantic property set of test image;Wherein Bj={ b1,j,b2,j,...,bK+Z,j, j=1,2 ..., N represents
Training image and the non-semantic attribute of jth of test image;
Given semantic attribute collection A={A1,A2,...,AM{ 0,1}, wherein M represents the number of semantic attribute, A to ∈i, i=
1,2 ..., M represents training image and the i-th semantic attribute subset of test image;By the described non-semantic property set obtained
Semantic attribute collection A is carried out supplementing and extending by B, and then structure obtains mixed attributes collection H={A, B}={A1,A2,...,AM,B1,
B2,...,BN}={ h1,...,hf,...,hM+N}∈{0,1};hf, f=1,2 ..., M+N is the f mixed attributes.
As the preferred version of the present invention, in described step 3, by training image low-level image feature collection X={x1,x2,...,xΚ}
∈Rd×KAs the training sample of mixed attributes grader, using mixed attributes collection H as the training sample mark of mixed attributes grader
Sign, and utilize multi-category support vector machines for each mixed attributes h in mixed attributes collection HfA mixed attributes is trained to divide
Class device;Training mixed attributes grader method particularly includes:
In formula, wfRepresent the f mixed attributes hfThe regression parameter of mixed attributes grader,Represent L2Norm, W=
{w1,w2,...,wM+NRepresent mixed attributes grader regression parameter collection, γ is for regulating mixed attributes grader complexity
Balance parameters;The regression parameter collection W={w of mixed attributes grader is obtained by solving formula (3)1,w2,...,wM+N, to obtain final product
Arrive each mixed attributes hfMixed attributes grader.
As the preferred version of the present invention, in described step 4, given Z class testing image low-level image feature collection { x '1,x
′2,...,x′Z}∈Rd×Z, test image blend attribute is predicted by the mixed attributes grader utilizing step 3 to obtain, and obtains
The prediction probability p of the i-th class testing image blend attribute (H | x 'i) method be:
In formula, x 'iRepresent the i-th class testing image low-level image feature, p (hf|x′i) represent that f of the i-th class testing image is mixed
Closing the prediction probability of attribute, attribute corresponding to maximum predicted probit is the test image blend attribute that prediction obtains.
As the preferred version of the present invention, in described step 5, according to Bayes theorem, obtain belonging to from test image blend
Property collection H to test image category label z Probability p (z | H):
Wherein, p (z) represents that test image belongs to the probability of test image category label z, and p (H) represents that test image has
The probability of mixed attributes collection H, p (H | z) represent the probability from test image category label z to test image blend property set H, with
The mode of discriminant determines from test image category label z to probability distribution p (H | z) of test image blend property set H:
In formula, HzRepresent test image actual mixed attributes collection;So, from test image low-level image feature x 'iTo test image
Posterior probability estimation p of class label z (z | x 'i) it is expressed as:
In formula, and p (z | hf) represent from the f mixed attributes hfTo the probability of test image category label z, p (hf|x′i) table
Show the low-level image feature x ' from i-th test imageiTo the f mixed attributes hfProbability,Represent that test image has f
Individual actual mixed attributesProbability,Represent from test image low-level image feature x 'iTo the f actual mixed attributes
Probability;
In above formula, it is assumed that it is all equal that category of test is divided into the probit of any class, then carrying out category of test
The impact of p (z) is ignored during Tag Estimation, and described p (z | x 'i) it is represented by:
As the preferred version of the present invention, in described step 6, at label allocated phase, pass through maximum a-posteriori estimation
The method predicting the i-th class testing image category label is:
From test image Z class label find out so that posterior probability estimation p (z | x 'i) maximum class label F
(x′i), and category label is distributed to test image, thus obtain testing image category label.
Beneficial effect: a kind of based on the direct forecast model of mixed attributes the zero sample image classification side that the present invention provides
Method, utilizes sparse coding to be reconstructed the low-level image feature of image, and then obtains the another kind of low-dimensional of image, compact expression side
Formula.Owing to the feature after this reconstruct does not has semantic information, therefore can named non-semantic attribute.By this extra dimension
Original semantic attribute is carried out supplementing and assisting by non-semantic attribute, attribute space is extended and constitutes mixed attributes.Non-
Semantic attribute can increase the diversity of semantic attribute such that it is able to the classification making semantic attribute similar is more prone to distinguish.Enter
One step, is applied to the mixed attributes of structure in DAP model so that the classification of attribute similarity is more prone to be distinguished originally.
This method combines direct attribute forecast model and the advantage of sparse coding, has the advantage that (1) is to semantic attribute
Supplemented and extended.Carry out supplementing and assisting to original semantic attribute by the non-semantic attribute of extra dimension, will belong to
Property space is extended and is constituted mixed attributes.(2) diversity of attribute space is added by extending non-semantic attribute.
(3) by increasing the diversity of attribute space so that the classification that semantic attribute is much like originally is more prone to be distinguished, thus carries
The discrimination of high zero sample image classification.
Accompanying drawing explanation
Fig. 1 is the flow chart of the inventive method.
Detailed description of the invention
Below in conjunction with the accompanying drawings the present invention is further described.
As it is shown in figure 1, this method specifically includes following steps:
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, comprises the steps:
Step 1, is learnt by sparse coding algorithm with training image low-level image feature collection, obtains base vector set;Specifically
For:
Given training image low-level image feature collection X={x1,x2,...,xΚ}∈Rd×K, wherein K is the classification of training image
Number, xi, i=1,2 ..., K is the i-th class training image low-level image feature, and d is the dimension of image low-level image feature, Rd×KRepresentation dimension is
The space of d × K;WithRepresenting base vector set, wherein N represents the number of base vector,J=1,2 ...,
N represents jth base vector;Sparse coding Algorithm Learning is then utilized to obtain the method for base vector set Φ specific as follows:
Step 1.1, random initializtion base vector set Φ;
Step 1.2, substitutes into training image low-level image feature collection X in following constraint equation:
In formula, bi,j, i=1,2 ..., K;J=1,2 ..., N is activation amount, represents the i-th class training image low-level image feature
xiJth sparse coding;λ represents weight attenuation quotient;Represent sparse regular terms;Represent L1Norm, c represents one
Individual constant, is used for limiting sparse degree;
Step 1.3, first fixing initialization base vector set Φ, solve the activation that constraint equation (1) can be made to minimize
Amount bi,j;Then activation amount b is fixedi,j, solve the base vector set Φ that constraint equation (1) can be made to minimize;
Step 1.4, constantly repeats step 1.3 until convergence, tries to achieve one group of base vector set representing image low-level image feature
Step 2, linearly weighs training image low-level image feature collection and test image low-level image feature collection with base vector set
Structure, obtains non-semantic property set, carries out supplementing and extending to semantic attribute collection, and then structure mixed attributes collection;Concrete steps are such as
Under:
Given test image set low-level image feature collection X '={ x '1,x′2,...,x′Z}∈Rd×Z, wherein Z is the class of test image
Other number, x 'i, i=1,2 ..., Z is the i-th class testing image low-level image feature, and d is the dimension of image low-level image feature, Rd×ZRepresent
Dimension is the space of d × Z;The base vector set obtained is learnt by step 1To training image low-level image feature
Collection X and test image low-level image feature collection X ' carries out linear reconstruction, obtainsI=1,2 ..., K andI=1,2 ..., Z;The method obtaining non-semantic property set B according to linear reconstruction result is:
Adjust activation amount bi,jMake formula (2) minimum, the set B={B finally given1,B2,...,BN{ 0,1} is i.e. ∈
Training image and the non-semantic property set of test image;Wherein Bj={ b1,j,b2,j,...,bK+Z,j, j=1,2 ..., N represents
Training image and the non-semantic attribute of jth of test image;
Given semantic attribute collection A={A1,A2,...,AM{ 0,1}, wherein M represents the number of semantic attribute, A to ∈i, i=
1,2 ..., M represents training image and the i-th semantic attribute subset of test image;By the described non-semantic property set obtained
Semantic attribute collection A is carried out supplementing and extending by B, and then structure obtains mixed attributes collection H={A, B}={A1,A2,...,AM,B1,
B2,...,BN}={ h1,...,hf,...,hM+N}∈{0,1};hf, f=1,2 ..., M+N is the f mixed attributes.
Step 3, utilizes training image low-level image feature to integrate each mixed attributes concentrated as mixed attributes and trains one to mix
Close attributive classification device;Specifically comprise the following steps that
By training image low-level image feature collection X={x1,x2,...,xΚ}∈Rd×KTraining sample as mixed attributes grader
This, using mixed attributes collection H as the training sample label of mixed attributes grader, and utilize multi-category support vector machines for mixing
Each mixed attributes h in property set HfTrain a mixed attributes grader;The concrete side of training mixed attributes grader
Method is:
In formula, wfRepresent the f mixed attributes hfThe regression parameter of mixed attributes grader,Represent L2Norm, W=
{w1,w2,...,wM+NRepresent mixed attributes grader regression parameter collection, γ is for regulating mixed attributes grader complexity
Balance parameters;The regression parameter collection W={w of mixed attributes grader is obtained by solving formula (3)1,w2,...,wM+N, to obtain final product
Arrive each mixed attributes hfMixed attributes grader.
In this step, the image low-level image feature collection X as the training sample of mixed attributes grader is that original bottom is special
Levying, in step 2, reconstruct is intended merely to obtain activation amount, thus obtains non-semantic attribute, can't change the low-level image feature of image.
Step 4, utilizes mixed attributes grader to be predicted test image blend attribute, obtains testing image blend and belongs to
The prediction probability of property;Specifically comprise the following steps that
In described step 4, given Z class testing image low-level image feature collection { x '1,x′2,...,x′Z}∈Rd×Z, utilize step 3
Test image blend attribute is predicted by the mixed attributes grader obtained, and obtains the pre-of the i-th class testing image blend attribute
Survey Probability p (H | x 'i) method be:
In formula, x 'iRepresent the i-th class testing image low-level image feature, p (hf|x′i) represent that f of the i-th class testing image is mixed
Closing the prediction probability of attribute, attribute corresponding to maximum predicted probit is the test image blend attribute that prediction obtains.
Step 5, the class label of test image is predicted by the test image blend attribute utilizing prediction to obtain, and obtains
Posterior probability estimation from test image low-level image feature to test image category label;Specifically comprise the following steps that
According to Bayes theorem, obtain Probability p from test image blend property set H to test image category label z (z |
H):
Wherein, p (z) represents that test image belongs to the probability of test image category label z, and p (H) represents that test image has
The probability of mixed attributes collection H, p (H | z) represent the probability from test image category label z to test image blend property set H, with
The mode of discriminant determines from test image category label z to probability distribution p (H | z) of test image blend property set H:
In formula, HzRepresent test image actual mixed attributes collection, be given by priori;So, from test image
Low-level image feature x 'iTo test image category label z posterior probability estimation p (z | x 'i) it is expressed as:
In formula, and p (z | hf) represent from the f mixed attributes hfTo the probability of test image category label z, p (hf|x′i) table
Show the low-level image feature x ' from i-th test imageiTo the f mixed attributes hfProbability,Represent that test image has f
Individual actual mixed attributesProbability,Represent from test image low-level image feature x 'iTo the f actual mixed attributes
Probability;
In above formula, it is assumed that it is all equal that category of test is divided into the probit of any class, then carrying out category of test
Tag Estimation time ignore the impact of p (z), described p (z | x 'i) it is represented by:
Step 6, finds out the class label maximum so that posterior probability estimation, and category label is distributed to test figure
Picture, thus obtains testing image category label;Particularly as follows:
At label allocated phase, predicted that by maximum a-posteriori estimation the method for the i-th class testing image category label is:
From test image Z class label find out so that posterior probability estimation p (z | x 'i) maximum class label F
(x′i), and category label is distributed to test image, thus obtain testing image category label.
The inventive method, is distinguished for the much like image category of semantic attribute is more difficult in the zero sample image classification
Problem, utilizes sparse coding to be reconstructed the low-level image feature of sample, will reconstruct after feature as non-semantic attribute to limited
Semantic attribute carry out supplementing and assisting, and constitute mixed attributes with original semantic attribute, thus increase the difference of attribute space
The opposite sex so that the classification of attribute similarity is more prone to be distinguished originally.
The above is only the preferred embodiment of the present invention, it should be pointed out that: for the ordinary skill people of the art
For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (7)
1. a zero sample image sorting technique based on the direct forecast model of mixed attributes, it is characterised in that include walking as follows
Rapid:
Step 1, is learnt by sparse coding algorithm with training image low-level image feature collection, obtains base vector set;
Step 2, carries out linear reconstruction with base vector set to training image low-level image feature collection and test image low-level image feature collection,
To non-semantic property set, carry out supplementing and extending to semantic attribute collection, and then structure mixed attributes collection;
Step 3, utilizes training image low-level image feature to integrate each mixed attributes concentrated as mixed attributes and trains a mixing to belong to
Property grader;
Step 4, utilizes mixed attributes grader to be predicted test image blend attribute, obtains testing image blend attribute
Prediction probability, attribute corresponding to maximum predicted probit is the test image blend attribute that prediction obtains;
Step 5, the class label of test image is predicted by the test image blend attribute utilizing prediction to obtain, and obtains from survey
Attempt as low-level image feature is to the posterior probability estimation of test image category label;
Step 6, finds out the class label maximum so that posterior probability estimation, and distributes to category label test image, by
This obtains testing image category label.
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 1, given training image low-level image feature collection X={x1,x2,...,xΚ}∈Rd×K, wherein K is training figure
The classification number of picture, xi, i=1,2 ..., K is the i-th class training image low-level image feature, and d is the dimension of image low-level image feature, Rd×K
Representation dimension is the space of d × K;WithRepresenting base vector set, wherein N represents the number of base vector,j
=1,2 ..., N represents jth base vector;Sparse coding Algorithm Learning is then utilized to obtain the method for base vector set Φ the most such as
Under:
Step 1.1, random initializtion base vector set Φ;
Step 1.2, substitutes into training image low-level image feature collection X in following constraint equation:
In formula, bi,j, i=1,2 ..., K;J=1,2 ..., N is activation amount, represents the i-th class training image low-level image feature xi?
J sparse coding;λ represents weight attenuation quotient;Represent sparse regular terms;Represent L1Norm, c represents a constant,
For limiting sparse degree;
Step 1.3, first fixing initialization base vector set Φ, solve the activation amount that constraint equation (1) can be made to minimize
bi,j;Then activation amount b is fixedi,j, solve the base vector set Φ that constraint equation (1) can be made to minimize;
Step 1.4, constantly repeats step 1.3 until convergence, tries to achieve one group of base vector set representing image low-level image feature
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 2, given test image set low-level image feature collection X '={ x '1,x′2,...,x′Z}∈Rd×Z, wherein Z is
The classification number of test image, x'i, i=1,2 ..., Z is the i-th class testing image low-level image feature, and d is image low-level image feature
Dimension, Rd×ZRepresentation dimension is the space of d × Z;The base vector set obtained is learnt by step 1To training
Image low-level image feature collection X and test image low-level image feature collection X ' carries out linear reconstruction, obtainsWith
AndThe method obtaining non-semantic property set B according to linear reconstruction result is:
Adjust activation amount bi,jMake formula (2) minimum, the set B={B finally given1,B2,...,BN{ 0,1} is i.e. training to ∈
Image and the non-semantic property set of test image;Wherein Bj={ b1,j,b2,j,...,bK+Z,j, j=1,2 ..., N represents training
Image and the non-semantic attribute of jth of test image;
Given semantic attribute collection A={A1,A2,...,AM{ 0,1}, wherein M represents the number of semantic attribute, A to ∈i, i=1,
2 ..., M represents training image and the i-th semantic attribute subset of test image;By the described non-semantic property set B obtained
Carry out supplementing and extending to semantic attribute collection A, and then structure obtains mixed attributes collection H={A, B}={A1,A2,...,AM,B1,
B2,...,BN}={ h1,...,hf,...,hM+N}∈{0,1};hf, f=1,2 ..., M+N is the f mixed attributes.
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 3, by training image low-level image feature collection X={x1,x2,...,xΚ}∈Rd×KClassify as mixed attributes
The training sample of device, using mixed attributes collection H as the training sample label of mixed attributes grader, and utilize many classification support to
Amount machine is each mixed attributes h in mixed attributes collection HfTrain a mixed attributes grader;Training mixed attributes classification
Device method particularly includes:
In formula, wfRepresent the f mixed attributes hfThe regression parameter of mixed attributes grader,Represent L2Norm, W={w1,
w2,...,wM+NRepresent mixed attributes grader regression parameter collection, γ is for regulating mixed attributes grader complexity
Balance parameters;The regression parameter collection W={w of mixed attributes grader is obtained by solving formula (3)1,w2,...,wM+N, i.e. obtain
Each mixed attributes hfMixed attributes grader.
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 4, given Z class testing image low-level image feature collection { x '1,x′2,...,x′Z}∈Rd×Z, utilize step 3 to obtain
To mixed attributes grader to test image blend attribute be predicted, obtain the prediction of the i-th class testing image blend attribute
Probability p (H | x 'i) method be:
In formula, x 'iRepresent the i-th class testing image low-level image feature, p (hf|x′i) represent that the f mixing of the i-th class testing image belongs to
Property prediction probability, attribute corresponding to maximum predicted probit is the test image blend attribute that prediction obtains.
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 5, according to Bayes theorem, obtain from test image blend property set H to test image category label
The Probability p of z (z | H):
Wherein, p (z) represents that test image belongs to the probability of test image category label z, and p (H) represents that test image has mixing
The probability of property set H, and p (H | z) represent the probability from test image category label z to test image blend property set H, to differentiate
The mode of formula determines from test image category label z to probability distribution p (H | z) of test image blend property set H:
In formula, HzRepresent test image actual mixed attributes collection;So, from test image low-level image feature x 'iTo test image category
Posterior probability estimation p of label z (z | x 'i) it is expressed as:
In formula, and p (z | hf) represent from the f mixed attributes hfTo the probability of test image category label z, p (hf|x′i) represent from
The low-level image feature x ' of i-th test imageiTo the f mixed attributes hfProbability,Represent that test image has the f in fact
Border mixed attributesProbability,Represent from test image low-level image feature x 'iTo the f actual mixed attributesGeneral
Rate;
In above formula, it is assumed that it is all equal that category of test is divided into the probit of any class, then carrying out category of test label
The impact of p (z) is ignored during prediction, and described p (z | x 'i) it is represented by:
A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes, it is special
Levy and be: in described step 6, at label allocated phase, predict the i-th class testing image category mark by maximum a-posteriori estimation
The method signed is:
From test image Z class label find out so that posterior probability estimation p (z | x 'i) maximum class label F (x 'i),
And category label is distributed to test image, thus obtain testing image category label.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610483014.2A CN106203472B (en) | 2016-06-27 | 2016-06-27 | A kind of zero sample image classification method based on the direct prediction model of mixed attributes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610483014.2A CN106203472B (en) | 2016-06-27 | 2016-06-27 | A kind of zero sample image classification method based on the direct prediction model of mixed attributes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106203472A true CN106203472A (en) | 2016-12-07 |
CN106203472B CN106203472B (en) | 2019-04-02 |
Family
ID=57461941
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610483014.2A Active CN106203472B (en) | 2016-06-27 | 2016-06-27 | A kind of zero sample image classification method based on the direct prediction model of mixed attributes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106203472B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106980876A (en) * | 2017-03-13 | 2017-07-25 | 南京邮电大学 | A kind of zero sample image recognition methods learnt based on distinctive sample attribute |
WO2018161217A1 (en) * | 2017-03-06 | 2018-09-13 | Nokia Technologies Oy | A transductive and/or adaptive max margin zero-shot learning method and system |
CN108846406A (en) * | 2018-04-18 | 2018-11-20 | 西安理工大学 | A kind of zero sample image classification method based on structure-borne |
CN109086710A (en) * | 2018-07-27 | 2018-12-25 | 杭州电子科技大学 | A kind of small sample target identification method based on mixed attributes study |
CN109886289A (en) * | 2019-01-08 | 2019-06-14 | 深圳禾思众成科技有限公司 | A kind of deep learning method, equipment and computer readable storage medium |
CN110073367A (en) * | 2017-01-19 | 2019-07-30 | 赫尔实验室有限公司 | The multiple view of compatible function of the utilization based on SOFT-MAX for zero sample learning is embedded in |
CN110427967A (en) * | 2019-06-27 | 2019-11-08 | 中国矿业大学 | The zero sample image classification method based on embedded feature selecting semanteme self-encoding encoder |
CN110582777A (en) * | 2017-05-05 | 2019-12-17 | 赫尔实验室有限公司 | Zero-sample machine vision system with joint sparse representation |
CN111126049A (en) * | 2019-12-14 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Object relation prediction method and device, terminal equipment and readable storage medium |
CN112257765A (en) * | 2020-10-16 | 2021-01-22 | 济南大学 | Zero sample image classification method and system based on unknown similarity class set |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512679A (en) * | 2015-12-02 | 2016-04-20 | 天津大学 | Zero sample classification method based on extreme learning machine |
-
2016
- 2016-06-27 CN CN201610483014.2A patent/CN106203472B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512679A (en) * | 2015-12-02 | 2016-04-20 | 天津大学 | Zero sample classification method based on extreme learning machine |
Non-Patent Citations (2)
Title |
---|
SHARMANSKA V 等: "Augmented attribute representations[A]", 《PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
巩萍 等: "基于属性关系图正则化特征选择的零样本分类", 《中国矿业大学学报》 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110073367A (en) * | 2017-01-19 | 2019-07-30 | 赫尔实验室有限公司 | The multiple view of compatible function of the utilization based on SOFT-MAX for zero sample learning is embedded in |
WO2018161217A1 (en) * | 2017-03-06 | 2018-09-13 | Nokia Technologies Oy | A transductive and/or adaptive max margin zero-shot learning method and system |
CN106980876A (en) * | 2017-03-13 | 2017-07-25 | 南京邮电大学 | A kind of zero sample image recognition methods learnt based on distinctive sample attribute |
CN110582777A (en) * | 2017-05-05 | 2019-12-17 | 赫尔实验室有限公司 | Zero-sample machine vision system with joint sparse representation |
CN108846406B (en) * | 2018-04-18 | 2022-04-22 | 西安理工大学 | Zero sample image classification method based on structure propagation |
CN108846406A (en) * | 2018-04-18 | 2018-11-20 | 西安理工大学 | A kind of zero sample image classification method based on structure-borne |
CN109086710A (en) * | 2018-07-27 | 2018-12-25 | 杭州电子科技大学 | A kind of small sample target identification method based on mixed attributes study |
CN109886289A (en) * | 2019-01-08 | 2019-06-14 | 深圳禾思众成科技有限公司 | A kind of deep learning method, equipment and computer readable storage medium |
CN110427967A (en) * | 2019-06-27 | 2019-11-08 | 中国矿业大学 | The zero sample image classification method based on embedded feature selecting semanteme self-encoding encoder |
CN111126049A (en) * | 2019-12-14 | 2020-05-08 | 中国科学院深圳先进技术研究院 | Object relation prediction method and device, terminal equipment and readable storage medium |
CN111126049B (en) * | 2019-12-14 | 2023-11-24 | 中国科学院深圳先进技术研究院 | Object relation prediction method, device, terminal equipment and readable storage medium |
CN112257765A (en) * | 2020-10-16 | 2021-01-22 | 济南大学 | Zero sample image classification method and system based on unknown similarity class set |
CN112257765B (en) * | 2020-10-16 | 2022-09-23 | 济南大学 | Zero sample image classification method and system based on unknown similarity class set |
Also Published As
Publication number | Publication date |
---|---|
CN106203472B (en) | 2019-04-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106203472A (en) | A kind of zero sample image sorting technique based on the direct forecast model of mixed attributes | |
Choi et al. | A tree-based context model for object recognition | |
CN105975916A (en) | Age estimation method based on multi-output convolution neural network and ordered regression | |
CN110348579A (en) | A kind of domain-adaptive migration feature method and system | |
CN108875816A (en) | Merge the Active Learning samples selection strategy of Reliability Code and diversity criterion | |
Zhao et al. | Modeling Stated preference for mobility-on-demand transit: a comparison of Machine Learning and logit models | |
CN106295697A (en) | A kind of based on semi-supervised transfer learning sorting technique | |
CN105740891B (en) | Target detection based on multi level feature selection and context model | |
CN110991532B (en) | Scene graph generation method based on relational visual attention mechanism | |
CN103020122A (en) | Transfer learning method based on semi-supervised clustering | |
CN103745233B (en) | The hyperspectral image classification method migrated based on spatial information | |
CN101794396A (en) | System and method for recognizing remote sensing image target based on migration network learning | |
CN103400144B (en) | Active learning method based on K-neighbor for support vector machine (SVM) | |
CN107563410A (en) | The sorting technique and equipment with multi-task learning are unanimously clustered based on topic categories | |
CN103489033A (en) | Incremental type learning method integrating self-organizing mapping and probability neural network | |
CN104966105A (en) | Robust machine error retrieving method and system | |
CN108090499A (en) | Data active mask method and system based on maximum information triple screening network | |
CN105005794A (en) | Image pixel semantic annotation method with combination of multi-granularity context information | |
CN106096661A (en) | Zero sample image sorting technique based on relative priority random forest | |
CN110119688A (en) | A kind of Image emotional semantic classification method using visual attention contract network | |
CN109635668A (en) | Facial expression recognizing method and system based on soft label integrated rolled product neural network | |
CN102646198B (en) | Mode recognition method of mixed linear SVM (support vector machine) classifier with hierarchical structure | |
Wang et al. | Linear twin svm for learning from label proportions | |
CN105975978A (en) | Semi-supervised multi-tag feature selection and classification method based on tag correlation | |
CN110378405A (en) | The Hyperspectral Remote Sensing Imagery Classification method of Adaboost algorithm based on transfer learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |