{"type":"ScholarlyArticle","title":"Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information","authors":[{"name":"Guanchun Wang","slug":"guanchun-wang","given":"Guanchun","family":"Wang","affiliation":"Xidian University"},{"name":"Xiangrong Zhang","slug":"xiangrong-zhang","given":"Xiangrong","family":"Zhang","affiliation":"Xidian University"},{"name":"Zelin Peng","slug":"zelin-peng","given":"Zelin","family":"Peng","affiliation":"Xidian University"},{"name":"Xu Tang","slug":"xu-tang","given":"Xu","family":"Tang","affiliation":"Xidian University"},{"name":"Huiyu Zhou","slug":"huiyu-zhou","given":"Huiyu","family":"Zhou","affiliation":"University of Leicester {gwang"},{"name":"Licheng Jiao","slug":"licheng-jiao","given":"Licheng","family":"Jiao","affiliation":"Xidian University"}],"abstract":"Weakly supervised object detection (WSOD) is a challenging task, in which image-level labels (e.g., categories of the instances in the whole image) are used to train an object detector. Many existing methods follow the standard multiple instance learning (MIL) paradigm and have achieved promising performance. However, the lack of deterministic information leads to part domination and missing instances. To address these issues, this paper focuses on identifying and fully exploiting the deterministic information in WSOD. We discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information. Based on this observation, we here propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD. Specifically, our method consists of two stages: NDI collecting and exploiting. In the collecting stage, we design several processes to identify and distill the NDI from negative instances online. In the exploiting stage, we utilize the extracted NDI to construct a novel negative contrastive learning mechanism and a negative guided instance selection strategy for dealing with the issues of part domination and missing instances, respectively. Experimental results on several public benchmarks including VOC 2007, VOC 2012 and MS COCO show that our method achieves satisfactory performance.","doi":"10.24963/ijcai.2022/192","url":"https://ijcai.org/proceedings/2022/192","pdf":"https://ijcai.org/proceedings/2022/0192.pdf","markdown":"https://ijcai.org/proceedings/2022/192.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/192","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Computer Vision","track":"Main Track","number":192,"pages":{"first":1378,"last":1384},"keywords":["Computer Vision: Recognition (object detection, categorization)","Machine Learning: Convolutional Networks","Machine Learning: Multi-instance","Machine Learning: Weakly Supervised Learning","Machine Learning: Multi-label"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986453","length_sec":68,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984596","length_sec":261,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Arbeláez et al., 2014] Pablo Arbeláez, Jordi Pont-Tuset, Jonathan T Barron, Ferran Marques, and Jitendra Malik. Multiscale combinatorial grouping. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recog- nition (CVPR), pages 328-335, 2014.","title":"Multiscale combinatorial grouping","authors":"Arbeláez","year":"2014","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bilen and Vedaldi, 2016] Hakan Bilen and Andrea Vedaldi. Weakly supervised deep detection networks. In Proceed- ings of the IEEE conference on computer vision and pat- tern recognition (CVPR), pages 2846-2854, 2016.","title":"Weakly supervised deep detection networks","authors":"Hakan Bilen, Andrea Vedaldi","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Everingham et al., 2010] Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisser- man. The pascal visual object classes (voc) challenge. In- ternational journal of computer vision (IJCV), 88(2):303- 338, 2010.","title":"The pascal visual object classes (voc) challenge. International journal of computer vision","authors":"Mark Everingham, Luc Van Gool, K I Christopher, John Williams, Andrew Winn, Zisserman","year":"2010","venue":"IJCV)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Girshick, 2015] Ross. Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (ICCV), pages 1440-1448, 2015.","title":"Fast r-cnn","authors":"Ross, Girshick","year":"2015","venue":"Proceedings of the IEEE international conference on computer vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Grill et al., 2020] Jean-Bastien Grill, Florian Strub, Floren- t Altché, Corentin Tallec, Pierre H Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhao- han Daniel Guo, Mohammad Gheshlaghi Azar, et al. Boot- strap your own latent: A new approach to self-supervised learning. In Advances in neural information processing systems (NeurIPS), 2020.","title":"Bootstrap your own latent: A new approach to self-supervised learning","authors":"Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Elena Pierre H Richemond, Carl Buchatskaya, Bernardo Doersch, Zhaohan Avila Pires, Mohammad Daniel Guo, Gheshlaghi Azar","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[He et al., 2020] Kaiming He, Haoqi Fan, Yuxin Wu, Sain- ing Xie, and Ross Girshick. Momentum contrast for un- supervised visual representation learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 9729-9738, 2020.","title":"Momentum contrast for unsupervised visual representation learning","authors":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, Ross Girshick","year":"2020","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huang et al., 2020] Zeyi Huang, Yang Zou, Vijayakumar Bhagavatula, and Dong Huang. Comprehensive atten- tion self-distillation for weakly-supervised object detec- tion. In Advances in neural information processing sys- tems (NeurIPS), 2020.","title":"Comprehensive attention self-distillation for weakly-supervised object detection","authors":"Zeyi Huang, Yang Zou, Vijayakumar Bhagavatula, Dong Huang","year":"2020","venue":"Advances in neural information processing systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Khosla et al., 2020] Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. Supervised con- trastive learning. In Advances in neural information pro- cessing systems (NeurIPS), 2020.","title":"Supervised contrastive learning","authors":"Khosla","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kim et al., 2019] Youngdong Kim, Junho Yim, Juseung Yun, and Junmo Kim. Nlnl: Negative learning for noisy la- bels. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 101-110, 2019.","title":"Nlnl: Negative learning for noisy labels","authors":"Kim","year":"2019","venue":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lin et al., 2014] Tsung-Yi Lin, Michael Maire, Serge Be- longie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Com- mon objects in context. In European conference on com- puter vision (ECCV), pages 740-755, 2014.","title":"Microsoft coco: Common objects in context","authors":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, C Lawrence, Zitnick","year":"2014","venue":"European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lin et al., 2020] Chenhao Lin, Siwen Wang, Dongqi Xu, Yu Lu, and Wayne Zhang. Object instance mining for weakly supervised object detection. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 11482-11489, 2020.","title":"Object instance mining for weakly supervised object detection","authors":"Lin","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Redmon et al., 2016] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: U- nified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recogni- tion (CVPR), pages 779-788, 2016.","title":"You only look once: Unified, real-time object detection","authors":"Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ren et al., 2015] Shaoqing Ren, Kaiming He, Ross Gir- shick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (NeurIPS), pages 91-99, 2015.","title":"Faster r-cnn: Towards real-time object detection with region proposal networks","authors":"Ren","year":"2015","venue":"Advances in neural information processing systems (NeurIPS)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ren et al., 2020] Zhongzheng Ren, Zhiding Yu, Xiaodong Yang, Ming-Yu Liu, Yong Jae Lee, Alexander G Schwing, and Jan Kautz. Instance-aware, context-focused, and memory-efficient weakly supervised object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 10598-10607, 2020.","title":"Instance-aware, context-focused, and memory-efficient weakly supervised object detection","authors":"Ren","year":"2020","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Tang et al., 2017] Peng Tang, Xinggang Wang, Xiang Bai, and Wenyu Liu. Multiple instance detection network with online instance classifier refinement. In Proceedings of the IEEE conference on computer vision and pattern recogni- tion (CVPR), pages 2843-2851, 2017.","title":"Multiple instance detection network with online instance classifier refinement","authors":"Peng Tang, Xinggang Wang, Xiang Bai, Wenyu Liu","year":"2017","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Tang et al., 2018] Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, and Alan Yuille. P- cl: Proposal cluster learning for weakly supervised object detection. IEEE transactions on pattern analysis and ma- chine intelligence (TPAMI), 42(1):176-191, 2018.","title":"Pcl: Proposal cluster learning for weakly supervised object detection","authors":"Peng Tang, Xinggang Wang, Song Bai, Wei Shen, Xiang Bai, Wenyu Liu, Alan Yuille","year":"2018","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Uijlings et al., 2013] Jasper RR Uijlings, Koen EA Van De Sande, Theo Gevers, and Arnold WM Smeulders. Se- lective search for object recognition. International journal of computer vision (IJCV), 104(2):154-171, 2013.","title":"Selective search for object recognition","authors":"Uijlings","year":"2013","venue":"International journal of computer vision","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wan et al., 2019] Fang Wan, Chang Liu, Wei Ke, Xi- angyang Ji, Jianbin Jiao, and Qixiang Ye. C-mil: Continu- ation multiple instance learning for weakly supervised ob- ject detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2199-2208, 2019.","title":"C-mil: Continuation multiple instance learning for weakly supervised object detection","authors":"Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye","year":"2019","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yang et al., 2019] Ke Yang, Dongsheng Li, and Yong Dou. Towards precise end-to-end weakly supervised object de- tection network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8372-8381, 2019.","title":"Towards precise end-to-end weakly supervised object detection network","authors":"Ke Yang, Dongsheng Li, Yong Dou","year":"2019","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yin et al., 2021] Yufei Yin, Jiajun Deng, Wengang Zhou, and Houqiang Li. Instance Mining with Class Feature Banks for Weakly Supervised Object Detection. In Pro- ceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 3190-3198, 2021.","title":"Instance Mining with Class Feature Banks for Weakly Supervised Object Detection","authors":"Yufei Yin, Jiajun Deng, Wengang Zhou, Houqiang Li","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zeng et al., 2019] Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, and Lei Zhang. Wsod2: Learn- ing bottom-up and top-down objectness distillation for weakly-supervised object detection. In Proceedings of the IEEE international conference on computer vision (IC- CV), pages 8292-8300, 2019.","title":"Wsod2: Learning bottom-up and top-down objectness distillation for weakly-supervised object detection","authors":"Zhaoyang Zeng, Bei Liu, Jianlong Fu, Hongyang Chao, Lei Zhang","year":"2019","venue":"Proceedings of the IEEE international conference on computer vision (IC-CV)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}