Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Coreset Selection for Object Detection (2404.09161v1)

Published 14 Apr 2024 in cs.CV and cs.LG

Abstract: Coreset selection is a method for selecting a small, representative subset of an entire dataset. It has been primarily researched in image classification, assuming there is only one object per image. However, coreset selection for object detection is more challenging as an image can contain multiple objects. As a result, much research has yet to be done on this topic. Therefore, we introduce a new approach, Coreset Selection for Object Detection (CSOD). CSOD generates imagewise and classwise representative feature vectors for multiple objects of the same class within each image. Subsequently, we adopt submodular optimization for considering both representativeness and diversity and utilize the representative vectors in the submodular optimization process to select a subset. When we evaluated CSOD on the Pascal VOC dataset, CSOD outperformed random selection by +6.4%p in AP$_{50}$ when selecting 200 images.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Coresets for ordered weighted clustering. In International Conference on Machine Learning, pages 744–753. PMLR, 2019.
  2. End-to-end object detection with transformers. In European conference on computer vision, pages 213–229. Springer, 2020.
  3. Dataset distillation by matching training trajectories. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4750–4759, 2022.
  4. Masked-attention mask transformer for universal image segmentation. 2022.
  5. Selection via proxy: Efficient data selection for deep learning. arXiv preprint arXiv:1906.11829, 2019.
  6. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR, 2009.
  7. Privacy for free: How does dataset condensation help privacy? In International Conference on Machine Learning, pages 5378–5396. PMLR, 2022.
  8. The pascal visual object classes challenge 2007 (voc2007) results. 2007.
  9. Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659, 2017.
  10. Deepcore: A comprehensive library for coreset selection in deep learning. In International Conference on Database and Expert Systems Applications, pages 181–195. Springer, 2022.
  11. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016.
  12. Coresets for clustering with fairness constraints. Advances in Neural Information Processing Systems, 32, 2019.
  13. On coresets for clustering in small dimensional euclidean spaces. arXiv preprint arXiv:2302.13737, 2023.
  14. Submodular combinatorial information measures with applications in machine learning. In Algorithmic Learning Theory, pages 722–754. PMLR, 2021.
  15. Consistency-based semi-supervised learning for object detection. Advances in neural information processing systems, 32, 2019.
  16. Talisman: targeted active learning for object detection with rare classes and slices using submodular mutual information. In European Conference on Computer Vision, pages 1–16. Springer, 2022.
  17. Submodular function maximization. Tractability, 3(71-104):3, 2014.
  18. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
  19. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
  20. Dataset distillation with infinitely wide convolutional networks. Advances in Neural Information Processing Systems, 34:5186–5198, 2021.
  21. Imbalance problems in object detection: A review. IEEE transactions on pattern analysis and machine intelligence, 43(10):3388–3415, 2020.
  22. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  23. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
  24. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS, pages 91–99, 2015.
  25. Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489, 2017.
  26. Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9627–9636, 2019.
  27. Wanderlust: Online continual object detection in the real world. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10829–10838, 2021.
  28. Dataset distillation. arXiv preprint arXiv:1811.10959, 2018.
  29. Frustratingly simple few-shot object detection. arXiv preprint arXiv:2003.06957, 2020.
  30. Submodularity in data subset selection and active learning. In International conference on machine learning, pages 1954–1963. PMLR, 2015.
  31. Max Welling. Herding dynamical weights to learn. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 1121–1128, 2009.
  32. Detectron2. https://github.com/facebookresearch/detectron2, 2019.
  33. Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2636–2645, 2020.
  34. Multiple instance active learning for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5330–5339, 2021.
  35. Dataset distillation using neural feature regression. Advances in Neural Information Processing Systems, 35:9813–9827, 2022.
  36. Detrs with collaborative hybrid assignments training, 2022.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets