{"type":"ScholarlyArticle","title":"SCMT: Self-Correction Mean Teacher for Semi-supervised Object Detection","authors":[{"name":"Feng Xiong","slug":"feng-xiong","given":"Feng","family":"Xiong","affiliation":"Alibaba Group"},{"name":"Jiayi Tian","slug":"jiayi-tian","given":"Jiayi","family":"Tian","affiliation":"Alibaba Group"},{"name":"Zhihui Hao","slug":"zhihui-hao","given":"Zhihui","family":"Hao","affiliation":"Alibaba Group"},{"name":"Yulin He","slug":"yulin-he","given":"Yulin","family":"He","affiliation":"Alibaba Group"},{"name":"Xiaofeng Ren","slug":"xiaofeng-ren","given":"Xiaofeng","family":"Ren","affiliation":"Alibaba Group"}],"abstract":"Semi-Supervised Object Detection (SSOD) aims to improve performance by leveraging a large amount of unlabeled data. Existing works usually adopt the teacher-student framework to enforce student to learn consistent predictions over the pseudo-labels generated by teacher. However, the performance of the student model is limited since the noise inherently exists in pseudo-labels. In this paper, we investigate the causes and effects of noisy pseudo-labels and propose a simple yet effective approach denoted as Self-Correction Mean Teacher(SCMT) to reduce the adverse effects. Specifically, we propose to dynamically re-weight the unsupervised loss of each student's proposal with additional supervision information from the teacher model, and assign smaller loss weights to possible noisy proposals. Extensive experiments on MS-COCO benchmark have shown the superiority of our proposed SCMT, which can significantly improve the supervised baseline by more than 11% mAP under all 1%, 5% and 10% COCO-standard settings, and surpasses state-of-the-art methods by about 1.5% mAP. Even under the challenging COCO-additional setting, SCMT still improves the supervised baseline by 4.9% mAP, and significantly outperforms previous methods by 1.2% mAP, achieving a new state-of-the-art performance.","doi":"10.24963/ijcai.2022/207","url":"https://ijcai.org/proceedings/2022/207","pdf":"https://ijcai.org/proceedings/2022/0207.pdf","markdown":"https://ijcai.org/proceedings/2022/207.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/207","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":207,"pages":{"first":1488,"last":1494},"keywords":["Computer Vision: Transfer, low-shot, semi- and un- supervised learning","Computer Vision: Recognition (object detection, categorization)"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986474","length_sec":90,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984617","length_sec":249,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Berthelot et al., 2019a] David Berthelot, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel. Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785, 2019.","title":"Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring","authors":"Berthelot","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berthelot et al., 2019b] David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin Raffel. Mixmatch: A holistic approach to semi- supervised learning. arXiv preprint arXiv:1905.02249, 2019.","title":"Mixmatch: A holistic approach to semisupervised learning","authors":"Berthelot","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bolya et al., 2020] Daniel Bolya, Sean Foley, James Hays, and Judy Hoffman. Tide: A general toolbox for identifying object detection errors. In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part III 16, pages 558-573. Springer, 2020.","title":"Tide: A general toolbox for identifying object detection errors","authors":"Daniel Bolya, Sean Foley, James Hays, Judy Hoffman","year":"2020","venue":"Computer Vision-ECCV 2020: 16th European Conference","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2019] Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu, et al. Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.","title":"Mmdetection: Open mmlab detection toolbox and benchmark","authors":"Kai Chen, Jiaqi Wang, Jiangmiao Pang, Yuhang Cao, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jiarui Xu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Jeong et al., 2019] Jisoo Jeong, Seungeui Lee, Jeesoo Kim, and Nojun Kwak. Consistency-based semi-supervised learning for object detection. Advances in neural infor- mation processing systems, 32:10759-10768, 2019.","title":"Consistency-based semi-supervised learning for object detection","authors":"Jisoo Jeong, Seungeui Lee, Jeesoo Kim, Nojun Kwak","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jiang et al., 2018] Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, and Yuning Jiang. Acquisition of localization confidence for accurate object detection. In Proceedings of the European conference on computer vision (ECCV), pages 784-799, 2018.","title":"Acquisition of localization confidence for accurate object detection","authors":"Jiang","year":"2018","venue":"Proceedings of the European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lee and others, 2013] Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896, 2013.","title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","authors":"Dong-Hyun Lee","year":"2013","venue":"Workshop on challenges in representation learning, ICML","doi":null,"url":null,"internal_url":null},{"position":8,"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, pages 740-755. Springer, 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","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lin et al., 2017a] Tsung-Yi Lin, Piotr Dollar, Ross Gir- shick, Kaiming He, Bharath Hariharan, and Serge Be- longie. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.","title":"Feature pyramid networks for object detection","authors":"Lin","year":"2017","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lin et al., 2017b] Tsung-Yi Lin, Priya Goyal, Ross Gir- shick, Kaiming He, and Piotr Dollár. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980-2988, 2017.","title":"Focal loss for dense object detection","authors":"Lin","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2021] Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, and Peter Vajda. Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480, 2021.","title":"Unbiased teacher for semi-supervised object detection","authors":"Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ren et al., 2015] Shaoqing Ren, Kaiming He, Ross Gir- shick, and Jian Sun. Faster r-cnn: Towards real-time ob- ject detection with region proposal networks. Advances in neural information processing systems, 28:91-99, 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","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Sajjadi et al., 2016] Mehdi Sajjadi, Mehran Javanmardi, and Tolga Tasdizen. Regularization with stochastic trans- formations and perturbations for deep semi-supervised learning. Advances in neural information processing sys- tems, 29:1163-1171, 2016.","title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","authors":"Mehdi Sajjadi, Mehran Javanmardi, Tolga Tasdizen","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Selvaraju et al., 2017] Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE international conference on com- puter vision, pages 618-626, 2017.","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","authors":"Michael Ramprasaath R Selvaraju, Abhishek Cogswell, Ramakrishna Das, Devi Vedantam, Dhruv Parikh, Batra","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sohn et al., 2020a] Kihyuk Sohn, David Berthelot, Chun- Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685, 2020.","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","authors":"Sohn","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Sohn et al., 2020b] Kihyuk Sohn, David Berthelot, Chun- Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D Cubuk, Alex Kurakin, Han Zhang, and Colin Raffel. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. arXiv preprint arXiv:2001.07685, 2020.","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","authors":"Sohn","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sohn et al., 2020c] Kihyuk Sohn, Zizhao Zhang, Chun- Liang Li, Han Zhang, Chen-Yu Lee, and Tomas Pfister. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757, 2020.","title":"A simple semi-supervised learning framework for object detection","authors":"Sohn","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Tang et al., 2021] Yihe Tang, Weifeng Chen, Yijun Luo, and Yuting Zhang. Humble teachers teach better students for semi-supervised object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pat- tern Recognition, pages 3132-3141, 2021.","title":"Humble teachers teach better students for semi-supervised object detection","authors":"Yihe Tang, Weifeng Chen, Yijun Luo, Yuting Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tarvainen and Valpola, 2017] Antti Tarvainen and Harri Valpola. Mean teachers are better role models: Weight- averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780, 2017.","title":"Mean teachers are better role models: Weightaveraged consistency targets improve semi-supervised deep learning results","authors":"Valpola Tarvainen, Antti Tarvainen, Harri Valpola","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Xie et al., 2020] Qizhe Xie, Minh-Thang Luong, Eduard Hovy, and Quoc V Le. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10687-10698, 2020.","title":"Self-training with noisy student improves imagenet classification","authors":"Xie","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Xu et al., 2021] Mengde Xu, Zheng Zhang, Han Hu, Jian- feng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, and Zicheng Liu. End-to-end semi-supervised object detection with soft teacher. arXiv preprint arXiv:2106.09018, 2021.","title":"End-to-end semi-supervised object detection with soft teacher","authors":"Mengde Xu, Zheng Zhang, Han Hu, Jianfeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhou et al., 2021] Qiang Zhou, Chaohui Yu, Zhibin Wang, Qi Qian, and Hao Li. Instant-teaching: An end-to-end semi-supervised object detection framework. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4081-4090, 2021.","title":"Instant-teaching: An end-to-end semi-supervised object detection framework","authors":"Qiang Zhou, Chaohui Yu, Zhibin Wang, Qi Qian, Hao Li","year":"2021","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}