2000 character limit reached
Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume (2403.19306v3)
Published 28 Mar 2024 in cs.CV
Abstract: Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse output, and propose Sparse Generation as a solution to make pseudo labels sparse. The method employs three processing stages (Mapping, Mask, Regression), constructs dense tensors through the relationship between data and detector model, optimizes three of its parameters, and obtains a sparse tensor, thereby indirectly obtaining higher quality pseudo labels, and addresses the model's density problem on low data volume. Additionally, we propose perspective-based matching, which provides more rational pseudo boxes for prediction missed on instances. In comparison to the SOTA method, on four datasets (MS COCO-val, RSOD, SIMD, Bullet-Hole), the experimental results demonstrated a significant advantage.
- Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
- End-to-end object detection with transformers. In European conference on computer vision, pp. 213–229. Springer, 2020.
- Points as queries: Weakly semi-supervised object detection by points. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 8823–8832, 2021.
- Point-to-box network for accurate object detection via single point supervision. In European Conference on Computer Vision, pp. 51–67. Springer, 2022.
- High-quality proposals for weakly supervised object detection. IEEE Transactions on Image Processing, 29:5794–5804, 2020.
- Ufo2: A unified pre-training framework for online and offline speech recognition. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE, 2023.
- Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580–587, 2014.
- Multisized object detection using spaceborne optical imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13:3032–3046, 2020.
- Lee, D.-H. 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, pp. 896. Atlanta, 2013.
- Object detection in optical remote sensing images: A survey and a new benchmark. ISPRS journal of photogrammetry and remote sensing, 159:296–307, 2020.
- Ambiguity-resistant semi-supervised learning for dense object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 15579–15588, 2023.
- Discovering regression-detection bi-knowledge transfer for unsupervised cross-domain crowd counting. Neurocomputing, 494:418–431, 2022.
- Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440, 2015.
- MacDougal, D. W. Newton’s gravity: an introductory guide to the mechanics of the universe. Springer Science & Business Media, 2012.
- An overview of deep semi-supervised learning. arXiv preprint arXiv:2006.05278, 2020.
- Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
- Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28, 2015.
- Ufo 2: A unified framework towards omni-supervised object detection. In European conference on computer vision, pp. 288–313. Springer, 2020.
- Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020a.
- A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757, 2020b.
- Sparse r-cnn: End-to-end object detection with learnable proposals. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 14454–14463, 2021.
- Multiple instance detection network with online instance classifier refinement. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2843–2851, 2017.
- Pcl: Proposal cluster learning for weakly supervised object detection. IEEE transactions on pattern analysis and machine intelligence, 42(1):176–191, 2018.
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
- Attention is all you need. Advances in neural information processing systems, 30, 2017.
- End-to-end semi-supervised object detection with soft teacher. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3060–3069, 2021.
- Wsod2: Learning bottom-up and top-down objectness distillation for weakly-supervised object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pp. 8292–8300, 2019.
- Weakly supervised object localization and detection: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(9):5866–5885, 2021.
- Dense teacher: Dense pseudo-labels for semi-supervised object detection. In European Conference on Computer Vision, pp. 35–50. Springer, 2022.
- Objects as points. arXiv preprint arXiv:1904.07850, 2019.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.