14.2.10 Open Set Recongnition

Chapter Contents (Back)
Recognition. Object Recognition. Open Set. Open World. Open Set Recognition. One issue is how to deal with all the out of distribution objects. Does the sample belong to training classes?

Zhang, H.[He], Patel, V.M.[Vishal M.],
Sparse Representation-Based Open Set Recognition,
PAMI(39), No. 8, August 2017, pp. 1690-1696.
IEEE DOI 1707
Not all classes presented during testing are known during training. Animals, Data models, Image reconstruction, Indexes, Pattern analysis, Testing, Training, Open set recognition, extreme value theory, sparse, representation-based, classification BibRef

de Oliveira Werneck, R.[Rafael], Raveaux, R.[Romain], Tabbone, S.[Salvatore], da Silva Torres, R.[Ricardo],
Learning cost function for graph classification with open-set methods,
PRL(128), 2019, pp. 8-15.
Elsevier DOI 1912
Graph matching, Cost learning, SVM, Open-set recognition BibRef
Earlier:
Learning Cost Functions for Graph Matching,
SSSPR18(345-354).
Springer DOI 1810
BibRef

Dang, S.A.[Sih-Ang], Cao, Z.J.[Zong-Jie], Cui, Z.Y.[Zong-Yong], Pi, Y.M.[Yi-Ming], Liu, N.Y.[Neng-Yuan],
Open Set Incremental Learning for Automatic Target Recognition,
GeoRS(57), No. 7, July 2019, pp. 4445-4456.
IEEE DOI 1907
Classifier with rejection option. Training, Target recognition, Learning systems, Computational modeling, Support vector machines, open set recognition (OSR) BibRef

Geng, C.X.[Chuan-Xing], Tao, L.[Lue], Chen, S.C.[Song-Can],
Guided CNN for generalized zero-shot and open-set recognition using visual and semantic prototypes,
PR(102), 2020, pp. 107263.
Elsevier DOI 2003
Convolutional prototype learning, Generalized zero-shot Learning, Open set recognition BibRef

Othman, E., Bazi, Y.[Yakoub], Melgani, F., Alhichri, H.[Haikel], Alajlan, N.[Naif], Zuair, M.,
Domain Adaptation Network for Cross-Scene Classification,
GeoRS(55), No. 8, August 2017, pp. 4441-4456.
IEEE DOI 1708
Computer architecture, Earth, Feature extraction, Feeds, Machine learning, Neural networks, Remote sensing, Cross-scene classification, distribution mismatch, domain adaptation, multisensor data, pretrained, convolutional, neural, network, (CNN) BibRef

Adayel, R.[Reham], Bazi, Y.[Yakoub], Alhichri, H.[Haikel], Alajlan, N.[Naif],
Deep Open-Set Domain Adaptation for Cross-Scene Classification based on Adversarial Learning and Pareto Ranking,
RS(12), No. 11, 2020, pp. xx-yy.
DOI Link 2006
BibRef

Loghmani, M.R.[Mohammad Reza], Vincze, M.[Markus], Tommasi, T.[Tatiana],
Positive-unlabeled learning for open set domain adaptation,
PRL(136), 2020, pp. 198-204.
Elsevier DOI 2008
Computer vision, Deep learning, Image classification, Domain adaptation, Open set recognition, Positive-Unlabelled learning BibRef

Fu, Y., Wang, X., Dong, H., Jiang, Y.G., Wang, M., Xue, X., Sigal, L.,
Vocabulary-Informed Zero-Shot and Open-Set Learning,
PAMI(42), No. 12, December 2020, pp. 3136-3152.
IEEE DOI 2011
Semantics, Vocabulary, Training data, Prototypes, Image recognition, Visualization, Learning systems, Vocabulary-informed learning, zero-shot learning BibRef

Liu, S.J.[Sheng-Jie], Shi, Q.[Qian], Zhang, L.P.[Liang-Pei],
Few-Shot Hyperspectral Image Classification With Unknown Classes Using Multitask Deep Learning,
GeoRS(59), No. 6, June 2021, pp. 5085-5102.
IEEE DOI 2106
Hyperspectral imaging, Image recognition, Image reconstruction, Machine learning, Training, Data models, open-set recognition BibRef

Cevikalp, H.[Hakan], Uzun, B.[Bedirhan], Köpüklü, O.[Okan], Ozturk, G.[Gurkan],
Deep compact polyhedral conic classifier for open and closed set recognition,
PR(119), 2021, pp. 108080.
Elsevier DOI 2106
Polyhedral conic classifier, Deep learning, Open set recognition, Image classification, Anomaly detection BibRef

Zhou, H.H.[Hao-Hong], Azzam, M.[Mohamed], Zhong, J.[Jian], Liu, C.[Cheng], Wu, S.[Si], Wong, H.S.[Hau-San],
Knowledge Exchange Between Domain-Adversarial and Private Networks Improves Open Set Image Classification,
IP(30), 2021, pp. 5807-5818.
IEEE DOI 2106
Adaptation models, Training, Task analysis, Knowledge engineering, Computational modeling, Data models, Benchmark testing, image classification BibRef

Feng, Z.[Zeyu], Xu, C.[Chang], Tao, D.C.[Da-Cheng],
Open-Set Hypothesis Transfer With Semantic Consistency,
IP(30), 2021, pp. 6473-6484.
IEEE DOI 2107
Adaptation models, Data models, Predictive models, Semantics, Training, Standards, Entropy, Open-set, domain adaptation, consistency regularization BibRef

Shermin, T.[Tasfia], Lu, G.J.[Guo-Jun], Teng, S.W.[Shyh Wei], Murshed, M.[Manzur], Sohel, F.[Ferdous],
Adversarial Network With Multiple Classifiers for Open Set Domain Adaptation,
MultMed(23), 2021, pp. 2732-2744.
IEEE DOI 2109
Adaptation models, Training, Loss measurement, Generators, Computational modeling, Data models, Task analysis, multi-classifier based weighting module BibRef

Geng, C.X.[Chuan-Xing], Huang, S.J.[Sheng-Jun], Chen, S.C.[Song-Can],
Recent Advances in Open Set Recognition: A Survey,
PAMI(43), No. 10, October 2021, pp. 3614-3631.
IEEE DOI 2109
Survey, Open Set Recognition. Training, Testing, Task analysis, Semantics, Face recognition, Data visualization, Open set recognition/classification, one-shot learning BibRef


Kodama, Y.[Yuto], Wang, Y.[Yinan], Kawakami, R.[Rei], Naemura, T.[Takeshi],
Open-set Recognition with Supervised Contrastive Learning,
MVA21(1-5)
DOI Link 2109
Training, Computer aided instruction, Training data, Feature extraction, Extraterrestrial measurements, Task analysis BibRef

Jafarzadeh, M.[Mohsen], Ahmad, T.[Touqeer], Dhamija, A.R.[Akshay Raj], Li, C.[Chunchun], Cruz, S.[Steve], Boult, T.E.[Terrance E.],
Automatic Open-World Reliability Assessment,
WACV21(1983-1992)
IEEE DOI 2106
Face recognition, Reliability theory, Reliability engineering, Classification algorithms, Reliability BibRef

Sachdeva, R.[Ragav], Cordeiro, F.R.[Filipe R.], Belagiannis, V.[Vasileios], Reid, I.[Ian], Carneiro, G.[Gustavo],
EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels,
WACV21(3606-3614)
IEEE DOI 2106
Training, Deep learning, Uncertainty, Annotations, Semantics, Training data, Focusing BibRef

Miller, D.[Dimity], Sünderhauf, N.[Niko], Milford, M.[Michael], Dayoub, F.[Feras],
Class Anchor Clustering: A Loss for Distance-based Open Set Recognition,
WACV21(3569-3577)
IEEE DOI 2106
Training, Protocols, Neural networks, Training data, Benchmark testing BibRef

Yu, Q.[Qing], Ikami, D.[Daiki], Irie, G.[Go], Aizawa, K.[Kiyoharu],
Multi-task Curriculum Framework for Open-set Semi-supervised Learning,
ECCV20(XII: 438-454).
Springer DOI 2010
BibRef

Rakshit, S.[Sayan], Tamboli, D.[Dipesh], Meshram, P.S.[Pragati Shuddhodhan], Banerjee, B.[Biplab], Roig, G.[Gemma], Chaudhuri, S.[Subhasis],
Multi-source Open-set Deep Adversarial Domain Adaptation,
ECCV20(XXVI:735-750).
Springer DOI 2011
BibRef

Rakshit, S.[Sayan], Banerjee, B.[Biplab], Roig, G.[Gemma], Chaudhuri, S.[Subhasis],
Unsupervised Multi-source Domain Adaptation Driven by Deep Adversarial Ensemble Learning,
GCPR19(485-498).
Springer DOI 1911
BibRef

Techapanurak, E.[Engkarat], Suganuma, M.[Masanori], Okatani, T.[Takayuki],
Hyperparameter-free Out-of-distribution Detection Using Cosine Similarity,
ACCV20(IV:53-69).
Springer DOI 2103
BibRef

Zhang, H.J.[Hong-Jie], Li, A.[Ang], Guo, J.[Jie], Guo, Y.[Yanwen],
Hybrid Models for Open Set Recognition,
ECCV20(III:102-117).
Springer DOI 2012
detect samples not belonging to any of the classes in its training set. BibRef

Bucci, S.[Silvia], Loghmani, M.R.[Mohammad Reza], Tommasi, T.[Tatiana],
On the Effectiveness of Image Rotation for Open Set Domain Adaptation,
ECCV20(XVI: 422-438).
Springer DOI 2010
BibRef

Chen, G.Y.[Guang-Yao], Qiao, L.[Limeng], Shi, Y.[Yemin], Peng, P.[Peixi], Li, J.[Jia], Huang, T.J.[Tie-Jun], Pu, S.L.[Shi-Liang], Tian, Y.H.[Yong-Hong],
Learning Open Set Network with Discriminative Reciprocal Points,
ECCV20(III:507-522).
Springer DOI 2012
BibRef

Zisselman, E.[Ev], Tamar, A.[Aviv],
Deep Residual Flow for Out of Distribution Detection,
CVPR20(13991-14000)
IEEE DOI 2008
detecting out-of-distribution examples. Gaussian distribution, Neural networks, Data models, Training, Jacobian matrices, Computer architecture, Maximum likelihood detection BibRef

Bertinetto, L.[Luca], Mueller, R.[Romain], Tertikas, K.[Konstantinos], Samangooei, S.[Sina], Lord, N.A.[Nicholas A.],
Making Better Mistakes: Leveraging Class Hierarchies With Deep Networks,
CVPR20(12503-12512)
IEEE DOI 2008
Standards, Measurement, Vegetation, Machine learning, Art, Visualization, Pipelines BibRef

Liu, B., Kang, H., Li, H., Hua, G., Vasconcelos, N.M.,
Few-Shot Open-Set Recognition Using Meta-Learning,
CVPR20(8795-8804)
IEEE DOI 2008
Training, Measurement, Task analysis, Robustness, Entropy, Image recognition, Face recognition BibRef

Pan, Y., Yao, T., Li, Y., Ngo, C., Mei, T.,
Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation,
CVPR20(13864-13872)
IEEE DOI 2008
Adaptation models, Data structures, Mutual information, Data models, Training, Entropy, Task analysis BibRef

Kundu, J.N.[Jogendra Nath], Venkatesh, R.M.[Rahul Mysore], Venkat, N.[Naveen], Revanur, A.[Ambareesh], Babu, R.V.[R. Venkatesh],
Class-incremental Domain Adaptation,
ECCV20(XIII:53-69).
Springer DOI 2011
BibRef

Kundu, J.N.[Jogendra Nath], Venkat, N.[Naveen], Revanur, A.[Ambareesh], Rahul, M.V., Babu, R.V.[R. Venkatesh],
Towards Inheritable Models for Open-Set Domain Adaptation,
CVPR20(12373-12382)
IEEE DOI 2008
Adaptation models, Task analysis, Data models, Predictive models, Computational modeling, Data privacy, Training BibRef

Feng, Q., Kang, G., Fan, H., Yang, Y.,
Attract or Distract: Exploit the Margin of Open Set,
ICCV19(7989-7998)
IEEE DOI 2004
data handling, decision theory, pattern classification, set theory, domain adaptation, domain shift, semantic structure, open set data, Benchmark testing BibRef

Liu, H.[Hong], Cao, Z.J.[Zhang-Jie], Long, M.S.[Ming-Sheng], Wang, J.M.[Jian-Min], Yang, Q.A.[Qi-Ang],
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation,
CVPR19(2922-2931).
IEEE DOI 2002
BibRef

Fu, J., Wu, X., Zhang, S., Yan, J.,
Improved Open Set Domain Adaptation with Backpropagation,
ICIP19(2506-2510)
IEEE DOI 1910
Open set domain adaptation, Back propagation, Symmetrical Kullback Leibler distance BibRef

Saito, K.[Kuniaki], Yamamoto, S.[Shohei], Ushiku, Y.[Yoshitaka], Harada, T.[Tatsuya],
Open Set Domain Adaptation by Backpropagation,
ECCV18(VI: 156-171).
Springer DOI 1810
BibRef

Yoshihashi, R.[Ryota], Shao, W.[Wen], Kawakami, R.[Rei], You, S.[Shaodi], Iida, M.[Makoto], Naemura, T.[Takeshi],
Classification-Reconstruction Learning for Open-Set Recognition,
CVPR19(4011-4020).
IEEE DOI 2002
BibRef

Tan, S.[Shuhan], Jiao, J.[Jiening], Zheng, W.S.[Wei-Shi],
Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration,
CVPR19(5389-5398).
IEEE DOI 2002
BibRef

Perera, P.[Pramuditha], Morariu, V.I.[Vlad I.], Jain, R.[Rajiv], Manjunatha, V.[Varun], Wigington, C.[Curtis], Ordonez, V.[Vicente], Patel, V.M.[Vishal M.],
Generative-Discriminative Feature Representations for Open-Set Recognition,
CVPR20(11811-11820)
IEEE DOI 2008
Does the sample belong to one of the trained classes? Training, Task analysis, Force, Image reconstruction, Shape, Semantics BibRef

Oza, P.[Poojan], Patel, V.M.[Vishal M.],
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition,
CVPR19(2302-2311).
IEEE DOI 2002
BibRef

Mundt, M., Pliushch, I., Majumder, S., Ramesh, V.,
Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?,
SDL-CV19(753-757)
IEEE DOI 2004
Bayes methods, image classification, neural nets, object detection, statistical analysis, statistical distributions, out of distribution detection BibRef

Sun, L.[Li], Yu, X.Y.[Xiao-Yi], Wang, L.[Liuan], Sun, J.[Jun], Inakoshi, H.[Hiroya], Kobayashi, K.[Ken], Kobashi, H.[Hiromichi],
Automatic Neural Network Search Method for Open Set Recognition,
ICIP19(4090-4094)
IEEE DOI 1910
Neural network search, open set, search space, feature distribution, center loss BibRef

Neal, L.[Lawrence], Olson, M.[Matthew], Fern, X.L.[Xiao-Li], Wong, W.K.[Weng-Keen], Li, F.X.[Fu-Xin],
Open Set Learning with Counterfactual Images,
ECCV18(VI: 620-635).
Springer DOI 1810
Label known plus detect unknown classes. BibRef

Wang, Y.S.[Yi-Sen], Liu, W.Y.[Wei-Yang], Ma, X.J.[Xing-Jun], Bailey, J.[James], Zha, H.Y.[Hong-Yuan], Song, L.[Le], Xia, S.T.[Shu-Tao],
Iterative Learning with Open-set Noisy Labels,
CVPR18(8688-8696)
IEEE DOI 1812
Noise measurement, Feature extraction, Cats, Training, Training data, Labeling, Convolutional neural networks BibRef

Gao, H.[Hua], Ekenel, H.K.[Hazim Kemal], Stiefelhagen, R.[Rainer],
Robust Open-Set Face Recognition for Small-Scale Convenience Applications,
DAGM10(393-402).
Springer DOI 1009
BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Multiple Kernel Learning, MKL .


Last update:Sep 12, 2021 at 22:38:33