14.5.5 Self-Supervised Learning for Detection

Tian, Q.[Qi], Wu, Y.[Ying], Yu, J.[Jie], Huang, T.S.[Thomas S.],
Self-supervised learning based on discriminative nonlinear features for image classification,
PR(38), No. 6, June 2005, pp. 903-917.
Elsevier DOI 0501
BibRef

Wu, Y.[Ying], Huang, T.S.[Thomas S.], Toyama, K.[Kentaro],
Self-Supervised Learning for Object Recognition based on Kernel Discriminant-EM Algorithm,
ICCV01(I: 275-280).
IEEE DOI 0106
BibRef

Zeng, Z.[Zeng], Xulei, Y.[Yang], Qiyun, Y.[Yu], Meng, Y.[Yao], Le, Z.[Zhang],
SeSe-Net: Self-Supervised deep learning for segmentation,
PRL(128), 2019, pp. 23-29.
Elsevier DOI 1912
Self-Supervised learning, Deep learning, Segmentation, U-Net BibRef

You, C.[Chong], Li, C.[Chi], Robinson, D.P.[Daniel P.], Vidal, R.[René],
Self-Representation Based Unsupervised Exemplar Selection in a Union of Subspaces,
PAMI(44), No. 5, May 2022, pp. 2698-2711.
IEEE DOI 2204
Clustering algorithms, Data models, Databases, Clustering methods, Optimization, Image reconstruction, subspace clustering BibRef

Shi, W.J.[Wen-Jie], Huang, G.[Gao], Song, S.[Shiji], Wang, Z.Y.[Zhuo-Yuan], Lin, T.[Tingyu], Wu, C.[Cheng],
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning,
PAMI(44), No. 5, May 2022, pp. 2712-2724.
IEEE DOI 2204
Task analysis, Decision making, Perturbation methods, Reinforcement learning, Jacobian matrices, Visualization, Games, decision-making process BibRef

Durrant, A.[Aiden], Leontidis, G.[Georgios],
Hyperspherically regularized networks for self-supervision,
IVC(124), 2022, pp. 104494.
Elsevier DOI 2208
Self-supervised learning, Representation learning, Representation separability, Image classification BibRef

Hénaff, O.J.[Olivier J.], Koppula, S.[Skanda], Alayrac, J.B.[Jean-Baptiste], van den Oord, A.[Aaron], Vinyals, O.[Oriol], Carreira, J.[João],
Efficient Visual Pretraining with Contrastive Detection,
ICCV21(10066-10076)
IEEE DOI 2203
Visualization, Transfer learning, Performance gain, Feature extraction, Data models, Computational efficiency, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Zhou, H.Y.[Hong-Yu], Lu, C.X.[Chi-Xiang], Yang, S.[Sibei], Han, X.G.[Xiao-Guang], Yu, Y.Z.[Yi-Zhou],
Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts,
ICCV21(3479-3489)
IEEE DOI 2203

WWW Link. Representation learning, Protocols, Codes, Computational modeling, Estimation, Task analysis, Medical, biological, and cell microscopy, BibRef

Jiang, Y.F.[Yi-Fan], Zhang, H.[He], Zhang, J.M.[Jian-Ming], Wang, Y.[Yilin], Lin, Z.[Zhe], Sunkavalli, K.[Kalyan], Chen, S.[Simon], Amirghodsi, S.[Sohrab], Kong, S.[Sarah], Wang, Z.Y.[Zhang-Yang],
SSH: A Self-Supervised Framework for Image Harmonization,
ICCV21(4812-4821)
IEEE DOI 2203
Measurement, Training, Visualization, Image color analysis, Perturbation methods, Training data, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Huang, S.Y.[Si-Yuan], Xie, Y.C.[Yi-Chen], Zhu, S.C.[Song-Chun], Zhu, Y.X.[Yi-Xin],
Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds,
ICCV21(6515-6525)
IEEE DOI 2203
Point cloud compression, Representation learning, Training, Solid modeling, Visualization, Supervised learning, Stereo, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Hu, K.[Kai], Shao, J.[Jie], Liu, Y.[Yuan], Raj, B.[Bhiksha], Savvides, M.[Marios], Shen, Z.Q.[Zhi-Qiang],
Contrast and Order Representations for Video Self-Supervised Learning,
ICCV21(7919-7929)
IEEE DOI 2203
Representation learning, Computational modeling, Predictive models, Task analysis, Videos, Representation learning BibRef

Qian, R.[Rui], Li, Y.X.[Yu-Xi], Liu, H.B.[Hua-Bin], See, J.[John], Ding, S.R.[Shuang-Rui], Liu, X.[Xian], Li, D.[Dian], Lin, W.Y.[Wei-Yao],
Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization,
ICCV21(7970-7981)
IEEE DOI 2203
Representation learning, Codes, Computational modeling, Semantics, Reliability, Task analysis, Video analysis and understanding, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Huang, D.[Deng], Wu, W.H.[Wen-Hao], Hu, W.[Weiwen], Liu, X.[Xu], He, D.L.[Dong-Liang], Wu, Z.H.[Zhi-Hua], Wu, X.[Xiangmiao], Tan, M.[Mingkui], Ding, E.[Errui],
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency,
ICCV21(8076-8085)
IEEE DOI 2203
Representation learning, Visualization, Image recognition, Codes, Noise measurement, Data mining, Video analysis and understanding, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Kim, D.H.[Dong-Hyun], Saito, K.[Kuniaki], Oh, T.H.[Tae-Hyun], Plummer, B.A.[Bryan A.], Sclaroff, S.[Stan], Saenko, K.[Kate],
CDS: Cross-Domain Self-supervised Pre-training,
ICCV21(9103-9112)
IEEE DOI 2203
Transfer learning, Task analysis, Standards, Transfer/Low-shot/Semi/Unsupervised Learning, Representation learning BibRef

Wang, G.[Guangrun], Wang, K.[Keze], Wang, G.[Guangcong], Torr, P.H.S.[Philip H.S.], Lin, L.[Liang],
Solving Inefficiency of Self-supervised Representation Learning,
ICCV21(9485-9495)
IEEE DOI 2203
Training, Representation learning, Computational modeling, Supervised learning, Benchmark testing, Task analysis, Representation learning BibRef

Patrick, M.[Mandela], Asano, Y.M.[Yuki M.], Kuznetsova, P.[Polina], Fong, R.[Ruth], Henriques, J.F.[João F.], Zweig, G.[Geoffrey], Vedaldi, A.[Andrea],
On Compositions of Transformations in Contrastive Self-Supervised Learning,
ICCV21(9557-9567)
IEEE DOI 2203
Codes, Benchmark testing, Encoding, Standards, Videos, Representation learning, Vision + other modalities BibRef

Hua, T.[Tianyu], Wang, W.X.[Wen-Xiao], Xue, Z.[Zihui], Ren, S.[Sucheng], Wang, Y.[Yue], Zhao, H.[Hang],
On Feature Decorrelation in Self-Supervised Learning,
ICCV21(9578-9588)
IEEE DOI 2203
Representation learning, Correlation, Robustness, Decorrelation, Covariance matrices, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Kotar, K.[Klemen], Ilharco, G.[Gabriel], Schmidt, L.[Ludwig], Ehsani, K.[Kiana], Mottaghi, R.[Roozbeh],
Contrasting Contrastive Self-Supervised Representation Learning Pipelines,
ICCV21(9929-9939)
IEEE DOI 2203
Representation learning, Training, Visualization, Pipelines, Benchmark testing, Data models, Representation learning, BibRef

Tian, Y.L.[Yong-Long], Hénaff, O.J.[Olivier J.], van den Oord, A.[Aäron],
Divide and Contrast: Self-supervised Learning from Uncurated Data,
ICCV21(10043-10054)
IEEE DOI 2203
Annotations, Benchmark testing, Data mining, Task analysis, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Zhao, Y.C.[Yu-Cheng], Wang, G.[Guangting], Luo, C.[Chong], Zeng, W.J.[Wen-Jun], Zha, Z.J.[Zheng-Jun],
Self-Supervised Visual Representations Learning by Contrastive Mask Prediction,
ICCV21(10140-10149)
IEEE DOI 2203
Training, Representation learning, Visualization, Head, Semantics, Performance gain, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Ayush, K.[Kumar], Uzkent, B.[Burak], Meng, C.L.[Chen-Lin], Tanmay, K.[Kumar], Burke, M.[Marshall], Lobell, D.[David], Ermon, S.[Stefano],
Geography-Aware Self-Supervised Learning,
ICCV21(10161-10170)
IEEE DOI 2203
Training, Image segmentation, Supervised learning, Semantics, Object detection, Task analysis, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Xiong, Y.[Yuwen], Ren, M.[Mengye], Zeng, W.Y.[Wen-Yuan], Waabi, R.U.[Raquel Urtasun],
Self-Supervised Representation Learning from Flow Equivariance,
ICCV21(10171-10180)
IEEE DOI 2203
Representation learning, Image segmentation, Semantics, Crops, Object detection, Streaming media, Representation learning, Vision for robotics and autonomous vehicles BibRef

Zhang, Z.[Zaiwei], Girdhar, R.[Rohit], Joulin, A.[Armand], Misra, I.[Ishan],
Self-Supervised Pretraining of 3D Features on any Point-Cloud,
ICCV21(10232-10243)
IEEE DOI 2203
Training, Solid modeling, Image recognition, Object detection, Computer architecture, Representation learning, 3D from multiview and other sensors BibRef

Koohpayegani, S.A.[Soroush Abbasi], Tejankar, A.[Ajinkya], Pirsiavash, H.[Hamed],
Mean Shift for Self-Supervised Learning,
ICCV21(10306-10315)
IEEE DOI 2203
Codes, Clustering algorithms, Task analysis, Residual neural networks, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Gavrilyuk, K.[Kirill], Jain, M.[Mihir], Karmanov, I.[Ilia], Snoek, C.G.M.[Cees G. M.],
Motion-Augmented Self-Training for Video Recognition at Smaller Scale,
ICCV21(10409-10418)
IEEE DOI 2203
Training, Optical losses, Knowledge engineering, Computational modeling, Semisupervised learning, Action and behavior recognition BibRef

Pantazis, O.[Omiros], Brostow, G.J.[Gabriel J.], Jones, K.E.[Kate E.], Aodha, O.M.[Oisin Mac],
Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring,
ICCV21(10563-10572)
IEEE DOI 2203
Training, Visualization, Transfer learning, Benchmark testing, Cameras, Biodiversity, Representation learning, Medical, biological, Recognition and classification BibRef

Zhang, L.Z.[Ling-Zhi], Du, W.Y.[Wei-Yu], Zhou, S.H.[Sheng-Hao], Wang, J.C.[Jian-Cong], Shi, J.B.[Jian-Bo],
Inpaint2Learn: A Self-Supervised Framework for Affordance Learning,
WACV22(3778-3787)
IEEE DOI 2202
Training, Affordances, Pipelines, Predictive models, Benchmark testing, Adversarial machine learning, Analysis and Understanding Scene Understanding BibRef

Mazumder, P.[Pratik], Singh, P.[Pravendra], Namboodiri, V.P.[Vinay P.],
Fair Visual Recognition in Limited Data Regime using Self-Supervision and Self-Distillation,
WACV22(3889-3897)
IEEE DOI 2202
Training, Deep learning, Adaptation models, Visualization, Computational modeling, Training data, Privacy and Ethics in Vision BibRef

Zheltonozhskii, E.[Evgenii], Baskin, C.[Chaim], Mendelson, A.[Avi], Bronstein, A.M.[Alex M.], Litany, O.[Or],
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels,
WACV22(387-397)
IEEE DOI 2202
Training, Upper bound, Neural networks, Semisupervised learning, Feature extraction, Robustness, Transfer, Large-scale Vision Applications BibRef

Reed, C.J.[Colorado J.], Yue, X.Y.[Xiang-Yu], Nrusimha, A.[Ani], Ebrahimi, S.[Sayna], Vijaykumar, V.[Vivek], Mao, R.[Richard], Li, B.[Bo], Zhang, S.H.[Shang-Hang], Guillory, D.[Devin], Metzger, S.[Sean], Keutzer, K.[Kurt], Darrell, T.J.[Trevor J.],
Self-Supervised Pretraining Improves Self-Supervised Pretraining,
WACV22(1050-1060)
IEEE DOI 2202
Computational modeling, Data models, Robustness, Task analysis, X-ray imaging, Convergence, Transfer, Few-shot, Vision for Aerial/Drone/Underwater/Ground Vehicles BibRef

Zhang, Z.[Zehua], Crandall, D.[David],
Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning,
WACV22(975-985)
IEEE DOI 2202
Representation learning, Deep learning, Codes, Semantics, Supervised learning, Benchmark testing, Transfer, Analysis and Understanding BibRef

Huynh, T.[Tri], Kornblith, S.[Simon], Walter, M.R.[Matthew R.], Maire, M.[Michael], Khademi, M.[Maryam],
Boosting Contrastive Self-Supervised Learning with False Negative Cancellation,
WACV22(986-996)
IEEE DOI 2202
Representation learning, Visualization, Codes, Computational modeling, Semantics, Boosting, Transfer, Few-shot, Semi- and Un- supervised Learning Deep Learning BibRef

Yamaguchi, S.[Shin'ya], Kanai, S.[Sekitoshi], Shioda, T.[Tetsuya], Takeda, S.[Shoichiro],
Image Enhanced Rotation Prediction for Self-Supervised Learning,
ICIP21(489-493)
IEEE DOI 2201
Shape, Predictive models, Network architecture, Benchmark testing, Task analysis, Image enhancement, Self-supervised learning, CNN BibRef

Chen, T.L.[Tian-Long], Frankle, J.[Jonathan], Chang, S.[Shiyu], Liu, S.[Sijia], Zhang, Y.[Yang], Carbin, M.[Michael], Wang, Z.Y.[Zhang-Yang],
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models,
CVPR21(16301-16311)
IEEE DOI 2111
Degradation, Image segmentation, Sensitivity, Computational modeling, Perturbation methods, Pattern recognition BibRef

Selvaraju, R.R.[Ramprasaath R.], Desai, K.[Karan], Johnson, J.[Justin], Naik, N.[Nikhil],
CASTing Your Model: Learning to Localize Improves Self-Supervised Representations,
CVPR21(11053-11062)
IEEE DOI 2111
Visualization, Correlation, Codes, Grounding, Crops, Robustness BibRef

Hou, L.[Luwei], Zhang, Y.[Yu], Fu, K.[Kui], Li, J.[Jia],
Informative and Consistent Correspondence Mining for Cross-Domain Weakly Supervised Object Detection,
CVPR21(9924-9933)
IEEE DOI 2111
Annotations, Collaboration, Object detection, Detectors, Generators, Pattern recognition BibRef

Yang, C.[Ceyuan], Wu, Z.R.[Zhi-Rong], Zhou, B.[Bolei], Lin, S.[Stephen],
Instance Localization for Self-supervised Detection Pretraining,
CVPR21(3986-3995)
IEEE DOI 2111
Location awareness, Transfer learning, Semantics, Object detection, Computer architecture, Pattern recognition BibRef

Ericsson, L.[Linus], Gouk, H.[Henry], Hospedales, T.M.[Timothy M.],
How Well Do Self-Supervised Models Transfer?,
CVPR21(5410-5419)
IEEE DOI 2111
Visualization, Image recognition, Image color analysis, Computational modeling, Object detection, Predictive models BibRef

Tang, Y.H.[Yi-He], Chen, W.F.[Wei-Feng], Luo, Y.J.[Yi-Jun], Zhang, Y.T.[Yu-Ting],
Humble Teachers Teach Better Students for Semi-Supervised Object Detection,
CVPR21(3131-3140)
IEEE DOI 2111
Training, Object detection, Detectors, Benchmark testing, Feature extraction, Data models BibRef

Gudovskiy, D., Hodgkinson, A., Yamaguchi, T., Tsukizawa, S.,
Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision,
CVPR20(9038-9046)
IEEE DOI 2008
Task analysis, Training, Kernel, Labeling, Artificial intelligence, Data models, Training data BibRef

Li, Y.D.[Yan-Dong], Huang, D.[Di], Qin, D.F.[Dan-Feng], Wang, L.Q.[Li-Qiang], Gong, B.Q.[Bo-Qing],
Improving Object Detection with Selective Self-supervised Self-training,
ECCV20(XXIX: 589-607).
Springer DOI 2010
BibRef

Lee, W.[Wonhee], Na, J.[Joonil], Kim, G.[Gunhee],
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations,
CVPR19(4979-4988).
IEEE DOI 2002
BibRef

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