Two Teachers Are Better Than One: Semi-supervised Elliptical Object Detection by Dual-Teacher Collaborative Guidance
Authors: 
Yu Liu, Longhan Feng, Qi Jia, Zezheng Liu, Zi-Huang CaoAuthors Info & Claims
Yu Liu, Longhan Feng, Qi Jia, Zezheng Liu, Zi-Huang CaoAuthors Info & ClaimsPages 6355 - 6363
Abstract
Elliptical Object Detection (EOD) is crucial yet challenging due to complex scenes and varying object characteristics. Existing methods often struggle with parameter configurations and lack adaptability in label-scarce scenarios. To address this, we propose a new semi-supervised teacher-student framework, namely Dual-Teacher Collaborative Guidance (DTCG), comprising a five-parameter teacher detector, a six-parameter teacher detector, and a student detector. DTCG allows the two teachers specializing in different regression approaches, and co-instructing the student within a unified model, so as to prevent errors and enhance performance. Additionally, a feature correlation module highlights differences between teacher features and employs deformable convolution to select advantageous features for final parameter regression. Furthermore, we devise a collaborative training strategy to update the two teachers asynchronously. Extensive experiments conducted on two widely recognized datasets affirm the superior performance of our DTCG over other leading competitors across various semi-supervised scenarios. Notably, our method achieves a 5.61% higher performance than the second best method when utilizing only 10% annotated data. Code is available at https://github.com/FengLongHan/DTCG.
References
[1]
Binghui Chen, Pengyu Li, Xiang Chen, Biao Wang, Lei Zhang, and Xian-Sheng Hua. 2022. Dense Learning based Semi-Supervised Object Detection. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4805--4814.
[2]
Cong Chen, Shouyang Dong, Ye Tian, Kunlin Cao, Li Liu, and Yuanhao Guo. 2022. Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection. IEEE Transactions on Multimedia, Vol. 24 (2022), 3679--3692.
[3]
Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei. 2017. Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision. 764--773.
[4]
Huixu Dong, Ehsan Asadi, Guangbin Sun, Dilip K Prasad, and I-Ming Chen. 2018. Real-time robotic manipulation of cylindrical objects in dynamic scenarios through elliptic shape primitives. IEEE Transactions on Robotics, Vol. 35, 1 (2018), 95--113.
[5]
Wenbo Dong, Pravakar Roy, Cheng Peng, and Volkan Isler. 2021. Ellipse R-CNN: Learning to infer elliptical object from clustering and occlusion. IEEE Transactions on Image Processing, Vol. 30 (2021), 2193--2206.
[6]
Michele Fornaciari, Andrea Prati, and Rita Cucchiara. 2014. A fast and effective ellipse detector for embedded vision applications. Pattern Recognition, Vol. 47, 11 (2014), 3693--3708.
[7]
Levente Hajder, Tekla Toth, and Zoltan Pusztai. 2020. Automatic estimation of sphere centers from images of calibrated cameras. arXiv preprint arXiv:2002.10217 (2020).
[8]
Kaiming He, Georgia Gkioxari, et al. 2017. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision. 2961--2969.
[9]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[10]
Wei Hua, Dingkang Liang, Jingyu Li, Xiaolong Liu, Zhikang Zou, Xiaoqing Ye, and Xiang Bai. 2023. SOOD: Towards Semi-Supervised Oriented Object Detection. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 15558--15567.
[11]
Jisoo Jeong, Seungeui Lee, Jeesoo Kim, and Nojun Kwak. 2019. Consistency-based Semi-supervised Learning for Object detection. In Advances in Neural Information Processing Systems, H. Wallach, H. Larochelle, A. Beygelzimer, F. dtextquotesingle Alché-Buc, E. Fox, and R. Garnett (Eds.), Vol. 32. Curran Associates, Inc.
[12]
Qi Jia, Xin Fan, Zhongxuan Luo, Lianbo Song, and Tie Qiu. 2017. A fast ellipse detector using projective invariant pruning. IEEE Transactions on Image Processing, Vol. 26, 8 (2017), 3665--3679.
[13]
Qi Jia, Xin Fan, Yang Yang, Xuxu Liu, Zhongxuan Luo, Qian Wang, Xinchen Zhou, and Longin Jan Latecki. 2023. Characteristic Mapping for Ellipse Detection Acceleration. IEEE Transactions on Image Processing (2023).
[14]
Jingen Jiang, Mingyang Zhao, et al. 2022. EDSF: Fast and Accurate Ellipse Detection via Disjoint-Set Forest. In 2022 IEEE International Conference on Multimedia and Expo (ICME). 1--6.
[15]
Euijin Kim, Miki Haseyama, et al. 2002. Fast and robust ellipse extraction from complicated images. In Proceedings of IEEE information technology and applications. Citeseer.
[16]
Feng Li, Bin He, Gang Li, Zhipeng Wang, and Rong Jiang. 2022. Shape-Biased Ellipse Detection Network With Auxiliary Task. IEEE Transactions on Instrumentation and Measurement, Vol. 71 (2022), 1--13.
[17]
Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, and Shanshan Zhang. 2022. Pseco: Pseudo labeling and consistency training for semi-supervised object detection. In European Conference on Computer Vision. Springer, 457--472.
[18]
Hanjun Li, Xingjia Pan, Ke Yan, Fan Tang, and Wei-Shi Zheng. 2022. Siod: Single instance annotated per category per image for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 14197--14206.
[19]
Yandong Li, Di Huang, Danfeng Qin, Liqiang Wang, and Boqing Gong. 2020. Improving object detection with selective self-supervised self-training. In European Conference on Computer Vision. Springer, 589--607.
[20]
Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. 2017. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2117--2125.
[21]
Qipeng Liu, Luojun Lin, Zhifeng Shen, and Zhifeng Yang. 2023. Periodically exchange teacher-student for source-free object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6414--6424.
[22]
Yen-Cheng Liu, Chih-Yao Ma, Xiaoliang Dai, Junjiao Tian, Peter Vajda, Zijian He, and Zsolt Kira. 2022. Open-set semi-supervised object detection. In European Conference on Computer Vision. Springer, 143--159.
[23]
Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, and Peter Vajda. 2021. Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480 (2021).
[24]
Changsheng Lu, Siyu Xia, et al. 2019. Arc-support line segments revisited: An efficient high-quality ellipse detection. IEEE Transactions on Image Processing, Vol. 29 (2019), 768--781.
[25]
Cai Meng, Zhaoxi Li, Xiangzhi Bai, and Fugen Zhou. 2020. Arc adjacency matrix-based fast ellipse detection. IEEE Transactions on Image Processing, Vol. 29 (2020), 4406--4420.
[26]
Viorica Pătrăucean, Pierre Gurdjos, et al. 2016. Joint a contrario ellipse and line detection. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 4 (2016), 788--802.
[27]
Ilija Radosavovic, Piotr Dollár, Ross Girshick, Georgia Gkioxari, and Kaiming He. 2018. Data distillation: Towards omni-supervised learning. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4119--4128.
[28]
Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, and Tomas Pfister. 2020. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020).
[29]
Yihe Tang, Weifeng Chen, Yijun Luo, and Yuting Zhang. 2021. Humble teachers teach better students for semi-supervised object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3132--3141.
[30]
Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, Vol. 30 (2017).
[31]
Zhi Tian, Chunhua Shen, Hao Chen, and Tong He. 2019. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision. 9627--9636.
[32]
Jesper E Van Engelen and Holger H Hoos. 2020. A survey on semi-supervised learning. Machine learning, Vol. 109, 2 (2020), 373--440.
[33]
Tianhao Wang, Changsheng Lu, Ming Shao, Xiaohui Yuan, and Siyu Xia. 2022. ElDet: An Anchor-free General Ellipse Object Detector. In Proceedings of the Asian Conference on Computer Vision (ACCV). 2580--2595.
[34]
Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, and Wayne Zhang. 2023. Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3240--3249.
[35]
Zhenyu Wang, Yali Li, Ye Guo, Lu Fang, and Shengjin Wang. 2021. Data-uncertainty guided multi-phase learning for semi-supervised object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4568--4577.
[36]
Qizhe Xie, Minh-Thang Luong, Eduard Hovy, and Quoc V Le. 2020. Self-training with noisy student improves imagenet classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10687--10698.
[37]
Mengde Xu, Zheng Zhang, Han Hu, Jianfeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, and Zicheng Liu. 2021. End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 3060--3069.
[38]
Qize Yang, Xihan Wei, Biao Wang, Xian-Sheng Hua, and Lei Zhang. 2021. Interactive self-training with mean teachers for semi-supervised object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5941--5950.
[39]
Byeonghyeop Yu, Johyun Shin, Gyeongjun Kim, Seungbin Roh, and Keemin Sohn. 2021. Non-anchor-based vehicle detection for traffic surveillance using bounding ellipses. IEEE Access, Vol. 9 (2021), 123061--123074.
[40]
Fangyuan Zhang, Tianxiang Pan, and Bin Wang. 2022. Semi-supervised object detection with adaptive class-rebalancing self-training. In Proceedings of the AAAI conference on artificial intelligence, Vol. 36. 3252--3261.
[41]
Jiacheng Zhang, Xiangru Lin, Wei Zhang, Kuo Wang, Xiao Tan, Junyu Han, Errui Ding, Jingdong Wang, and Guanbin Li. 2023. Semi-DETR: Semi-Supervised Object Detection With Detection Transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 23809--23818.
[42]
Jiacheng Zhang, Xiangru Lin, Wei Zhang, Kuo Wang, Xiao Tan, Junyu Han, Errui Ding, Jingdong Wang, and Guanbin Li. 2023. Semi-detr: Semi-supervised object detection with detection transformers. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 23809--23818.
[43]
Hongyu Zhou, Zheng Ge, Songtao Liu, Weixin Mao, Zeming Li, Haiyan Yu, and Jian Sun. 2022. Dense teacher: Dense pseudo-labels for semi-supervised object detection. In European Conference on Computer Vision. Springer, 35--50.
[44]
Kexue Zhou, Min Zhang, Honghui Zhao, Rui Tang, Sheng Lin, Xi Cheng, and Hai Wang. 2023. Arbitrary-Oriented Ellipse Detector for Ship Detection in Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 16 (2023), 7151--7162.
[45]
Qiang Zhou, Chaohui Yu, Zhibin Wang, Qi Qian, and Hao Li. 2021. Instant-teaching: An end-to-end semi-supervised object detection framework. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 4081--4090.
Index Terms
- Two Teachers Are Better Than One: Semi-supervised Elliptical Object Detection by Dual-Teacher Collaborative Guidance
Recommendations
Weakly- and Semi-Supervised Fast Region-Based CNN for Object Detection
AbstractLearning an effective object detector with little supervision is an essential but challenging problem in computer vision applications. In this paper, we consider the problem of learning a deep convolutional neural network (CNN) based object ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Self-supervised Mean Teacher for Semi-supervised Chest X-Ray Classification
Machine Learning in Medical ImagingAbstractThe training of deep learning models generally requires a large amount of annotated data for effective convergence and generalisation. However, obtaining high-quality annotations is a laboursome and expensive process due to the need of expert ...
Comments
Information & Contributors
Information
Published In
October 2024
11719 pages
ISBN:9798400706868
DOI:10.1145/3664647
- General Chairs:
- Jianfei Cai,
- Mohan Kankanhalli,
- Balakrishnan Prabhakaran,
- Susanne Boll,
- Program Chairs:
- Ramanathan Subramanian,
- Liang Zheng,
- Vivek K. Singh,
- Pablo Cesar,
- Lexing Xie,
- Dong Xu
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Natural Science Foundation
- Liaoning Provincial NSF
Conference
MM '24
Sponsor:
MM '24: The 32nd ACM International Conference on Multimedia
October 28 - November 1, 2024
Melbourne VIC, Australia
Acceptance Rates
MM '24 Paper Acceptance Rate 1,150 of 4,385 submissions, 26%;
Overall Acceptance Rate 2,145 of 8,556 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 112Total Downloads
- Downloads (Last 12 months)112
- Downloads (Last 6 weeks)64
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in