The DOI matches its Crossref record; 56 of the 57 references it cites were found in a registry or an index.
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization
Open accessAbstract
We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos. Most existing weakly-supervised methods localize only the most discriminative parts of an object rather than all relevant parts, which leads to suboptimal performance. Our key idea is to hide patches in a training image randomly, forcing the network to seek other relevant parts when the most discriminative part is hidden. Our approach only needs to modify the input image and can work with any network designed for object localization. During testing, we do not need to hide any patches. Our Hide-and-Seek approach obtains superior performance compared to previous methods for weakly-supervised object localization on the ILSVRC dataset. We also demonstrate that our framework can be easily extended to weakly-supervised action localization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“However, various types of industrial image defects do not meet all the above assumptions [42,43].”
From An Improved VGG19 Transfer Learning Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets (2021) · cites this paper as [43]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
(2014) · Cited by 33,419
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
(2016) · Cited by 31,590
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839
Flagged first, then by citations
1 of the 57 references couldn’t be matched to a known paper.
Research works printed but not linked: 5
- jiang, 2014, THUMOS Challenge Action Recognition with A Large Number of Classes
- jhuang, 2013, Towards undestanding action recognition, ICCV
- 10.1109/CVPR.2016.311 · DOI · Paper page
- cinbis, 2015, Weakly supervised object localization with multi-fold multiple instance learning
- wan, 2013, Regularization of neural network using dropconnect, ICML
Cited by
Sorted by citations
CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
Yun, S., Han, D., Chun, S., Oh, S. J., Yoo, Y., & Choe, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00612 · Cited by 5,400
“Object localization methods [32, 2] also utilize the regional dropout techniques for improving the localization ability of CNNs.”
BackgroundMethodInfluentialRandom Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7000 · Cited by 3,617
Semi-Supervised Semantic Segmentation With Cross-Consistency Training
Ouali, Y., Hudelot, C., & Tami, M. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01269 · Cited by 1,077
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
Jiang, P.-T., Zhang, C., Hou, Q., Cheng, M., & Wei, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3089943 · Cited by 960
“Recently, a lot of WSOL methods [59], [60], [1], [8], [60], [61], [62], [63] utilizing attention methods have been proposed, such as CAM [1], Grad-CAM [2], and ACoL [8].”
MethodA Comprehensive Survey of Image Augmentation Techniques for Deep Learning
Xu, M., Yoon, S., Fuentes, A., & Park, D. S. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109347 · Cited by 736
“Occlusion: Hide-and-Seek [23], Cutout [24], Random Eras-ing [25], GridMask [26].”
BackgroundMethodInfluentialAdversarial Complementary Learning for Weakly Supervised Object Localization
Zhang, X., Wei, Y., Feng, J., Yang, Y., & Huang, T. S. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00144 · Cited by 625
Imbalance Problems in Object Detection: A Review
Öksüz, K., Çam, B. C., Kalkan, S., & Akbaş, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2981890 · Cited by 629
Self-challenging Improves Cross-Domain Generalization
Huang, Z., Wang, H., Xing, E. P., & Huang, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_8 · Cited by 597
Tell Me Where to Look: Guided Attention Inference Network
Li, K., Wu, Z., Peng, K., Ernst, J., & Fu, Y. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00960 · Cited by 564
FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference
Lee, J., Kim, E., Lee, S., Lee, J., & Yoon, S. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00541 · Cited by 475
“Image-level hiding and erasure have been proposed [19, 27, 31] as ways of preventing a classifier from focusing exclusively on the discriminative parts of objects.”
BackgroundAttention-Based Dropout Layer for Weakly Supervised Object Localization
Choe, J., & Shim, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00232 · Cited by 420
“These results also support the observation that the accuracy of localization and classification are in a trade-off relationship when applying the drop mask [35].”
BackgroundMethodResultInfluentialWeakly Supervised Action Localization by Sparse Temporal Pooling Network
Nguyen, P., Han, B., Liu, T., & Prasad, G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00706 · Cited by 407
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
Zhang, J., Fan, D.-P., Dai, Y., Anwar, S., Saleh, F. S., Zhang, T., & Barnes, N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00861 · Cited by 423
Rescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01531-2 · Cited by 400
Deep Learning for Medical Image-Based Cancer Diagnosis
Jiang, X., Hu, Z., Wang, S., & Zhang, Y. (2023) · Cancers · doi:10.3390/cancers15143608 · Cited by 409
W-TALC: Weakly-Supervised Temporal Activity Localization and Classification
Paul, S., Roy, S., & Roy–Chowdhury, A. K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01225-0_35 · Cited by 350
Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Sun, G., Wang, W., Dai, J., & Gool, L. V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_21 · Cited by 348
Weakly-Supervised Semantic Segmentation via Sub-Category Exploration
Chang, Y.-T., Wang, Q., Hung, W.-C., Piramuthu, R., Tsai, Y., & Yang, M. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00901 · Cited by 338
“Numerous approaches [34, 39] deliberately hide or erase the region of an object, forcing models to seek more diverse parts.”
BackgroundMulti-class Token Transformer for Weakly Supervised Semantic Segmentation
Xu, L., Ouyang, W., Bennamoun, M., Boussaïd, F., & Xu, D. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00427 · Cited by 331
“A few methods developed heuristic strategies, such as “Hide & Seek” [31] and Erasing [40], applied either on images [24, 49] or feature maps [16,21] to drive the network to learn novel object patterns.”
MethodAutoLoc: Weakly-Supervised Temporal Action Localization in Untrimmed Videos
Shou, Z., Gao, H., Zhang, L., Miyazawa, K., & Chang, S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01270-0_10 · Cited by 289
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
Lee, J., Kim, E., & Yoon, S. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00406 · Cited by 297
Weakly Supervised Object Localization and Detection: A Survey
Zhang, D., Han, J., Cheng, G., & Yang, M.-H. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3074313 · Cited by 277
Hierarchical Deep Stereo Matching on High-Resolution Images
Yang, G., Manela, J., Happold, M., & Ramanan, D. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00566 · Cited by 275
“To force the model to rely more on contextual cues, we apply asymmetric masking, which randomly replaces a rectangular region in the target view with mean RGB values of the whole image [29].”
MethodBackground Suppression Network for Weakly-Supervised Temporal Action Localization
Lee, P., Uh, Y., & Byun, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6793 · Cited by 21
Feature Refinement and Filter Network for Person Re-Identification
Ning, X., Gong, K., Li, W., Zhang, L., Bai, X. P., & Tian, S. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3043026 · Cited by 258
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization
Liu, D., Jiang, T., & Wang, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00139 · Cited by 248
“Hide-and-Seek [25] hid random frame sequences while training to force the network responsive to multiple relevant parts.”
BackgroundSelf-produced Guidance for Weakly-Supervised Object Localization
Zhang, X., Wei, Y., Kang, G., Yang, Y., & Huang, T. S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01258-8_37 · Cited by 248
“…51.46 Backprop on GoogLeNet [41] 61.31 50.55 AlexNet-GAP [1] 67.19 52.16 VGGnet-GAP [1] 57.20 45.14 GoogLeNet-GAP [1] 56.40 43.00 GoogLeNet-HaS-32 [2] 54.53 - VGGnet-ACoL [20] 54.17 40.57 GoogLeNet-ACoL [20] 53 baseline methods on the ILSVRC 2016 dataset, as it has more than 1.2 million images of…”
MethodInfluentialLeafGAN: An Effective Data Augmentation Method for Practical Plant Disease Diagnosis
Huu, Q., Uga, H., Kagiwada, S., & Iyatomi, H. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3041499 · Cited by 272
Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection
Ren, Z., Yu, Z., Yang, X., Liu, M.-Y., Lee, Y. J., Schwing, A. G., & Kautz, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01061 · Cited by 237
Self-citationTS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
Gao, W., Wan, F., Pan, X., Peng, Z., Tian, Q. C., Han, Z., Zhou, B., & Ye, Q. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00288 · Cited by 243
“tion [30, 43, 45] or adversarial training [7, 20, 40, 47, 45, 30].”
MethodDANet: Divergent Activation for Weakly Supervised Object Localization
Xue, H., Liu, C., Wan, F., Jiao, J., Ji, X., & Ye, Q. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00669 · Cited by 225
“propagation [40], data argumentation [13], dilated convolution [31], and adversarial erasing [37, 12] to expand class activation maps and pursue full object extent.”
BackgroundHu, T., Qi, H., Huang, Q., & Lu, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09891 · Cited by 262
“Before our work, random spatial image augmentation methods [19, 3, 24], such as image cropping and image dropping, have been proposed and proved to be effective in improving the robustness of deep models.”
BackgroundMethodLearning a Mixture of Granularity-Specific Experts for Fine-Grained Categorization
Zhang, L., Huang, S., Liu, W., & Tao, D. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00842 · Cited by 219
“Given attention map we construct input for next expert using technique similar to weakly supervised object localization [46, 22, 29].”
MethodRegional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation
Zhou, T., Zhang, M., Zhao, F., & Li, J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00426 · Cited by 216
“…more complete object regions by, e.g ., region growing to expand initial responses [24, 30, 60], adversarial erasing in a hide-and-seek fashion [23, 32, 33, 64], feature enrichment to collect within-image contexts [66, 72], seeking auxiliary saliency supervisions [35, 71, 74], or self-supervised…”
BackgroundKernelized Memory Network for Video Object Segmentation
Seong, H., Hyun, J., & Kim, E. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58542-6_38 · Cited by 204
Evaluating Weakly Supervised Object Localization Methods Right
Choe, J., Oh, S. J., Lee, S., Chun, S., Akata, Z., & Shim, H. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00320 · Cited by 215
“WSOL techniques since CAM have focused on this limitation and have proposed different architectural [57, 58, 6] and dataaugmentation [26, 55] solutions.”
BackgroundMethodInfluentialImproving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing
Liu, X., Wang, Z., Shao, J., Wang, X., & Li, H. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00205 · Cited by 202
“Previous works has explored erasing image regions for object detection [29], person re-identification [10], weakly supervised detection [25, 7] and semantic segmentation [30].”
BackgroundMethodMin-Entropy Latent Model for Weakly Supervised Object Detection
Wan, F., Wei, P., Jiao, J., Han, Z., & Ye, Q. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00141 · Cited by 198
Weakly-Supervised Action Localization by Generative Attention Modeling
Shi, B., Dai, Q., Mu, Y., & Wang, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00109 · Cited by 187
“Hide-and-Seek [44] Weak - 36.”
Weakly-Supervised Action Localization With Background Modeling
Nguyen, P., Ramanan, D., & Fowlkes, C. C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00560 · Cited by 182
3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization
Narayan, S., Cholakkal, H., Khan, F. S., & Shao, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00877 · Cited by 181
“The work of [25, 14, 28] use action category labels in videos for temporal localization, whereas [13] uses point-level supervision to spatio-temporally localize the actions.”
BackgroundWeakly-Supervised Video Moment Retrieval via Semantic Completion Network
Lin, Z., Zhao, Z., Zhang, Z., Wang, Q., & Liu, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6820 · Cited by 173
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
Zhang, C., Cao, M., Yang, D., Chen, J., & Zou, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01575 · Cited by 170
“Hide-and-seek [36] and MAAN [43] try to extend the discriminative regions via randomly hiding patches or suppressing the dominant response, respectively.”
BackgroundOn Feature Normalization and Data Augmentation
Li, B., Wu, F., Lim, S.-N., Belongie, S., & Weinberger, K. Q. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01220 · Cited by 176
“Many subsequent papers proposed alternative flavors of this augmentation approach based on similar insights [4, 5, 7, 27, 28, 36, 51, 63, 70].”
BackgroundMethodUnified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing
Tian, Y., Li, D., & Xu, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58580-8_26 · Cited by 164
Liu, Y., Wu, Y.-H., Wen, P., Shi, Y., Qiu, Y., & Cheng, M. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3023152 · Cited by 160
“These methods either adopt image hiding and erasure to prevent a classifier from focusing exclusively on the discriminative parts of objects [23], [31], [49], or expand the CAM using feature-level processing [27], [29], [50]–[53] and region growing [30], [32], [54], [55] techniques.”
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Zhai, Y., Wang, L., Tang, W., Zhang, Q., Yuan, J., & Hua, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58539-6_3 · Cited by 156
Complementary Patch for Weakly Supervised Semantic Segmentation
Zhang, F., Gu, C., Zhang, C., & Dai, Y. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00715 · Cited by 160
Temporal Complementary Learning for Video Person Re-identification
Hou, R., Chang, H., Ma, B., Shan, S., & Chen, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58595-2_24 · Cited by 155
Masked Discrimination for Self-supervised Learning on Point Clouds
Liu, H., Cai, M., & Lee, Y. J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20086-1_38 · Cited by 175
Self-citationFine-Grained Recognition: Accounting for Subtle Differences between Similar Classes
Sun, G., Cholakkal, H., Khan, S. H., Khan, F. S., & Shao, L. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6882 · Cited by 153
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
Wang, Y., Shen, X., Hu, S. X., Yuan, Y., Crowley, J. L., & Vaufreydaz, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01414 · Cited by 155
“The methods can be divided to two groups: models initialized with ImageNet-1K supervised pre-training [3, 13, 22, 46, 71, 76, 77] and models inilialized with ImageNet-1K self-supervised pre-training [45].”
SF-Net: Single-Frame Supervision for Temporal Action Localization
Ma, F., Zhu, L., Yang, Y., Zha, S., Kundu, G., Feiszli, M., & Shou, Z. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58548-8_25 · Cited by 152
Weakly supervised convolutional LSTM approach for tool tracking in laparoscopic videos
Nwoye, C. I., Mutter, D., Marescaux, J., & Padoy, N. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-01958-6 · Cited by 149
“According to [20], this enables the network to learn meticulously the necessary details of the object of interest.”
BackgroundMethodInfluentialXie, J., Xiang, J., Chen, J., Hou, X., Zhao, X., & Shen, L. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00106 · Cited by 155
“To solve the above problem, various methods [6, 24, 31, 42–44, 48, 49] have been proposed.”
A survey of semi- and weakly supervised semantic segmentation of images
Zhang, M., Zhou, Y. Z., Zhao, J., Man, Y., Liu, B., & Yao, R. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09792-7 · Cited by 148
“The idea of hide-and-seek is also applied by Singh and Lee (2017).”
BackgroundWeakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
Luo, Z., Guillory, D., Shi, B., Ke, W., Wan, F., Darrell, T., & Xu, H. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58526-6_43 · Cited by 140
High-Quality Proposals for Weakly Supervised Object Detection
Cheng, G., Yang, J., Gao, D., Guo, L., & Han, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2987161 · Cited by 140
“More recently, WSOD has attracted considerable attention because of its broad applications [1]–[12].”
BackgroundActivation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation
Qin, J., Wu, J., Xiao, X., Li, L., & Wang, X. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20108 · Cited by 140
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Alwassel, H., Giancola, S., & Ghanem, B. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00356 · Cited by 136
“Video understanding is thriving in the computer vision community, and it manifests in several challenging tasks such as action classification [13, 34, 41, 69], activity localization [16, 36, 86], and video captioning [25, 53, 71, 88].”
BackgroundA New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
Liu, C., Wang, Z., Wang, S., Tang, T., Tao, Y., Yang, C., Li, H., Liu, X., & Fan, X. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3100059 · Cited by 137
“Among all the methods, information-dropping methods ( i.e. , GridMask, RErase, Cutout, HaS) perform worse than than the baseline method because dropping information could make the class-imbalance problem more serious.”
A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
Islam, A., Long, C., & Radke, R. J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i2.16256 · Cited by 17
Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks
Liu, Z., Wang, L., Zhang, Q., Gao, Z., Niu, Z., Zheng, N., & Hua, G. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00400 · Cited by 122
“W ea k ly -s u p er v is ed Hide-and-Seek [32] 19.”
BackgroundMethodInfluentialMai, J., Yang, M., & Luo, W. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00879 · Cited by 128
“Recently, various methods [41, 43, 28, 13, 40, 39, 2] have been developed to handle this challenging task.”
BackgroundMethodInfluentialSaliencyMix: A Saliency Guided Data Augmentation Strategy for Better RegularizationPreprint
Uddin, A. F. M. S., Monira, M. S., Shin, W., Chung, T., & Bae, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.01791 · Cited by 185
“Dropout (Nitish et al., 2014; Tompson et al., 2015) and regional dropout (Junsuk & Hyunjung, 2019; Terrance & Graham, 2017; Golnaz et al., 2018; Singh & Lee, 2017; Zhun et al., 2017) are two established training strategies where the former randomly turns off some internal activations and later…”
Weakly-supervised Temporal Action Localization by Uncertainty Modeling
Lee, P., Wang, J., Lu, Y., & Byun, H. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16280 · Cited by 22
“(Nguyen et al. 2018) propose a sparsity regularization, while (Singh and Lee 2017) and (Yuan et al. 2019) extend small discriminative parts.”
BackgroundRethinking the Route Towards Weakly Supervised Object Localization
Zhang, C.-L., Cao, Y.-H., & Wu, J. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01347 · Cited by 122
Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
Liu, Y., Sheng, L., Shao, J., Yan, J., Xiang, S., & Pan, C. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240567 · Cited by 119
“Recently, many researches on WSD [2, 8, 17, 26, 46] have been conducted.”
BackgroundRethinking Class Activation Mapping for Weakly Supervised Object Localization
Bae, W., Noh, J., & Kim, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58555-6_37 · Cited by 118
Li, J., Li, W., Sisk, A. E. J., Ye, H., Wallace, W. D., Speier, W. F., & Arnold, C. W. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104253 · Cited by 125
ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization
He, B., Yang, X., Kang, L., Cheng, Z., Zhou, X., & Shrivastava, A. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01355 · Cited by 120
Choe, J., Lee, S., & Shim, H. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2999099 · Cited by 119
What makes instance discrimination good for transfer learning?
Zhao, N., Wu, Z., Lau, R. W. H., & Lin, S. (2020) · arXiv · doi:10.48550/arxiv.2006.06606 · Cited by 115
Inter-Image Communication for Weakly Supervised Localization
Zhang, X., Wei, Y., & Yang, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58529-7_17 · Cited by 114
Survey: Image mixing and deleting for data augmentation
Naveed, H., Anwar, S., Hayat, M., Javed, K., & Mian, A. S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107791 · Cited by 138
Group-Wise Learning for Weakly Supervised Semantic Segmentation
Zhou, T., Li, L., Li, X., Feng, C.-M., Li, J., & Shao, L. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3132834 · Cited by 108
Uncertainty Guided Collaborative Training for Weakly Supervised Temporal Action Detection
Yang, W., Zhang, T., Yu, X., Tian, Q. C., Zhang, Y., & FengWu, F. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00012 · Cited by 110
“And existing works can be mainly categorized into three groups, learning background suppression attention weights [31, 32, 36, 21, 53], learning discriminative features [35, 30] and erasing discriminative segments during training [40, 56, 54].”
BackgroundTN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection
Zhang, L., Chang, X., Liu, J., Luo, M., Li, Z., Yao, L., & Hauptmann, A. G. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3183586 · Cited by 107
“Singh et al. [47] proposed the Hide and Seek technique, which randomly hides regions to force the model to focus on multiple relevant parts of an activity, and then thresholds class activation maps to obtain the activity’s start-end times.”
BackgroundSiddiquee, M. M. R., Zhou, Z., Tajbakhsh, N., Feng, R., Gotway, M. B., Bengio, Y., & Liang, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00028 · Cited by 105
“Pinheiro and Collobert [23] replaced the original GAP with a log-sum-exponential pooling layer, while other works [28, 36] aim to force the CAM to discover the complementary parts rather than just the most discriminative parts of the objects.”
BackgroundMethodShallow Feature Matters for Weakly Supervised Object Localization
Wei, J., Wang, Q., Li, Z., Wang, S., Zhou, S., & Cui, S. R. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00593 · Cited by 104
Deep Anatomical Context Feature Learning for Cephalometric Landmark Detection
Oh, K., Oh, I.-S., Le, V. N. T., & Lee, D. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3002582 · Cited by 105
“The studies [29]–[31] for the weakly supervised object localization presented a drawback of CNNs that tends to focus on the most discriminative part, and proposed a novel paradigm that forces networks to seek other relevant parts by hiding important image patches while training.”
BackgroundGonzález-Gonzalo, C., Thee, E. F., Klaver, C. C. W., Lee, A. Y., Schlingemann, R. O., Tufail, A., Verbraak, F., & Sánchez, C. I. (2022) · Progress in Retinal and Eye Research · doi:10.1016/j.preteyeres.2021.101034 · Cited by 103
“Firstly, attribution techniques were developed and optimized with natural images, and it has been shown that they localize only the most discriminative regions (Singh and Lee, 2017).”
Looking Beyond Single Images for Weakly Supervised Semantic Segmentation Learning
Wang, W., Sun, G., & Gool, L. V. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3168530 · Cited by 100
“The third class drives the classification network to focus on different parts of objects, through hiding/erasing some high response regions [17], [18], [19], [37].”
BackgroundAction Unit Memory Network for Weakly Supervised Temporal Action Localization
Luo, W., Zhang, T., Yang, W., Liu, J., Mei, T., Wu, F., & Zhang, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00984 · Cited by 99
“To relieve this problem, the weakly supervised setting that only requires video-level category labels is proposed [37, 55, 39, 37, 55, 53, 29, 30, 45, 46].”
Kang, S., Hu, Z., Liu, L., Zhang, K., & Cao, Z. (2025) · Electronics · doi:10.3390/electronics14061104 · Cited by 130
Zeng, R., Gan, C., Chen, P., Huang, W., Wu, Q., & Tan, M. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2922108 · Cited by 96
EPIC-KITCHENS-100Preprint
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.13256 · Cited by 153
“Previous weakly-supervised approaches utilised video-level or transcript supervision, where the set [64,65,66,67,68,69] or sequence [70,71,72,73,74,75] of actions in the video are used in training, without temporal bounds.”
BackgroundC-WSL: Count-Guided Weakly Supervised Localization
Gao, M., Li, A., Yu, R., Morariu, V. I., & Davis, L. S. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01246-5_10 · Cited by 96
A Comprehensive Survey on Data Augmentation
Wang, Z., Wang, P., Liu, K., Wang, P., Fu, Y., Lu, C.-T., Aggarwal, C. C., Pei, J., & Zhou, Y. (2025) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2025.3622600 · Cited by 206
“and [68] focus on improving robustness with the help of STL components.”
Temporal Structure Mining for Weakly Supervised Action Detection
Yu, T., Ren, Z., Li, Y., Yan, E., Xu, N., & Yuan, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00562 · Cited by 91
Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video Parsing
Wu, Y., & Yang, Y. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00138 · Cited by 95
“There are also weakly-supervised works [24, 26, 29, 36, 44] proposed for action localization.”
BackgroundForeground-Action Consistency Network for Weakly Supervised Temporal Action Localization
Huang, L., Wang, L., & Li, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00790 · Cited by 94
“1, the attention mechanism (either class-agnostic attention or class-wise attention) usually suffers from the discrepancy [36, 49, 19] between classification and detection, i.e ., the attention scores being concentrated around most discrim-a inative action snippets or wrongly focus on background…”
Step-by-step Erasion, One-by-one Collection
Zhong, J.-X., Li, N., Kong, W., Zhang, T., Li, T. H., & Li, G. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240511 · Cited by 103
“ansfer between video frames and web images for fine-grained action localization. Wang etal.[48] establish the UntrimmedNets to work on weakly supervised action detection problem. The work proposed in [39] shares a similar training strategy with our approach, and the difference is that it trains a single classifier by…”
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
Gao, J., Chen, M., & Xu, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01937 · Cited by 95
“Currently, most existing approaches can be roughly divided into three groups, namely attention-based methods [26, 26, 39, 42, 49, 56, 57, 68], MIL-based methods [32, 43, 45, 48, 54], and erasing-based methods [62, 72, 74].”
BackgroundUnveiling the Potential of Structure Preserving for Weakly Supervised Object Localization
Pan, X., Gao, Y., Lin, Z., Tang, F., Dong, W., Yuan, H., Huang, F., & Xu, C. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01147 · Cited by 95
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization
Yu, X., Wang, J., Zhao, Y. S., & Gao, Y. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109131 · Cited by 96
Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
Xu, Y., Zhang, C., Cheng, Z., Xie, J., Niu, Y. F., Pu, S., & Wu, F. Q. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019070 · Cited by 89
Combinational Class Activation Maps for Weakly Supervised Object Localization
Yang, S., Kim, Y., Kim, Y., & Kim, C. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093566 · Cited by 90
Wan, X., Zhang, X., & Liu, L. (2021) · Applied Sciences · doi:10.3390/app11062606 · Cited by 90
“However, various types of industrial image defects do not meet all the above assumptions [42,43].”
BackgroundGeometry Constrained Weakly Supervised Object Localization
Lu, W., Jia, X., Xie, W., Shen, L., Zhou, Y., & Duan, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58574-7_29 · Cited by 89
Metadata
- Authors
- Singh, K. K., & Lee, Y. J.
- Affiliations
- Intel (United States) (US)
- University of California, Davis (US)
- Venue
- 2017 IEEE International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2017-10
- Pages
- 3544-3553
- OpenAlex
- W2606520630
- Cited by
- 724
- References
- 57
- Citations by year
- 2026: 19 · 2025: 49 · 2024: 74 · 2023: 121 · 2022: 129 · 2021: 137 · 2020: 98 · 2019: 70 · 2018: 25 · 2017: 2
- FWCI
- 15.59
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Nvidia
- Amazon Web Services
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- weakly supervised object localization, data augmentation, image classification, video action recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
