Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
120 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
3 tokens/sec
DeepSeek R1 via Azure Pro
55 tokens/sec
2000 character limit reached

AirShot: Efficient Few-Shot Detection for Autonomous Exploration (2404.05069v1)

Published 7 Apr 2024 in cs.CV

Abstract: Few-shot object detection has drawn increasing attention in the field of robotic exploration, where robots are required to find unseen objects with a few online provided examples. Despite recent efforts have been made to yield online processing capabilities, slow inference speeds of low-powered robots fail to meet the demands of real-time detection-making them impractical for autonomous exploration. Existing methods still face performance and efficiency challenges, mainly due to unreliable features and exhaustive class loops. In this work, we propose a new paradigm AirShot, and discover that, by fully exploiting the valuable correlation map, AirShot can result in a more robust and faster few-shot object detection system, which is more applicable to robotics community. The core module Top Prediction Filter (TPF) can operate on multi-scale correlation maps in both the training and inference stages. During training, TPF supervises the generation of a more representative correlation map, while during inference, it reduces looping iterations by selecting top-ranked classes, thus cutting down on computational costs with better performance. Surprisingly, this dual functionality exhibits general effectiveness and efficiency on various off-the-shelf models. Exhaustive experiments on COCO2017, VOC2014, and SubT datasets demonstrate that TPF can significantly boost the efficacy and efficiency of most off-the-shelf models, achieving up to 36.4% precision improvements along with 56.3% faster inference speed. Code and Data are at: https://github.com/ImNotPrepared/AirShot.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Q. Fan, W. Zhuo, C.-K. Tang, and Y.-W. Tai, “Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 4013–4022.
  2. H. Hu, S. Bai, A. Li, J. Cui, and L. Wang, “Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 10 185–10 194.
  3. B. Kang, Z. Liu, X. Wang, F. Yu, J. Feng, and T. Darrell, “Few-Shot Object Detection via Feature Reweighting,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 8420–8429.
  4. Y.-X. Wang, D. Ramanan, and M. Hebert, “Meta-Learning to Detect Rare Objects,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 9925–9934.
  5. X. Wang, T. E. Huang, T. Darrell, J. E. Gonzalez, and F. Yu, “Frustratingly simple few-shot object detection,” arXiv preprint arXiv:2003.06957, 2020.
  6. C. Wang, Y. Qiu, W. Wang, Y. Hu, S. Kim, and S. Scherer, “Unsupervised Online Learning for Robotic Interestingness with Visual Memory,” IEEE Transactions on Robotics, pp. 1–15, 2021.
  7. C. Wang, W. Wang, Y. Qiu, Y. Hu, and S. Scherer, “Visual Memorability for Robotic Interestingness via Unsupervised Online Learning,” in Proceedings of the European Conference on Computer Vision (ECCV), 2020, pp. 52–68.
  8. B. Li, C. Wang, P. Reddy, S. Kim, and S. Scherer, “Airdet: Few-shot detection without fine-tuning for autonomous exploration,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXXIX.   Springer, 2022, pp. 427–444.
  9. S. Kim, C. Wang, B. Li, and S. Scherer, “Robotic Interestingness via Human-Informed Few-Shot Object Detection,” in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 1756–1763.
  10. Y. Li, H. Zhu, Y. Cheng, W. Wang, C. S. Teo, C. Xiang, P. Vadakkepat, and T. H. Lee, “Few-shot object detection via classification refinement and distractor retreatment,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15 395–15 403.
  11. Z. Yang, C. Zhang, R. Li, Y. Xu, and G. Lin, “Efficient few-shot object detection via knowledge inheritance,” IEEE Transactions on Image Processing, vol. 32, pp. 321–334, 2022.
  12. Z. Fan, Y. Ma, Z. Li, and J. Sun, “Generalized few-shot object detection without forgetting,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4527–4536.
  13. L. Qiao, Y. Zhao, Z. Li, X. Qiu, J. Wu, and C. Zhang, “Defrcn: Decoupled faster r-cnn for few-shot object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 8681–8690.
  14. B. Sun, B. Li, S. Cai, Y. Yuan, and C. Zhang, “FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 7352–7362.
  15. J. Wu, S. Liu, D. Huang, and Y. Wang, “Multi-Scale Positive Sample Refinement for Few-Shot Object Detection,” in Proceedings of the European Conference on Computer Vision (ECCV), 2020, pp. 456–472.
  16. L. Zhang, S. Zhou, J. Guan, and J. Zhang, “Accurate Few-Shot Object Detection With Support-Query Mutual Guidance and Hybrid Loss,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 14 424–14 432.
  17. W. Zhang, Y.-X. Wang, and D. A. Forsyth, “Cooperating rpn’s improve few-shot object detection,” arXiv preprint arXiv:2011.10142, 2020.
  18. R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), vol. 2.   IEEE, 2006, pp. 1735–1742.
  19. R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
  20. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
  21. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “SSD: Single Shot Multibox Detector,” in Proceedings of the European Conference on Computer Vision (ECCV), 2016, pp. 21–37.
  22. J. Redmon and A. Farhadi, “Yolo9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7263–7271.
  23. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015.
  24. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
  25. J. Redmon and A. Farhadi, “Yolov3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
  26. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature Pyramid Networks for Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2117–2125.
  27. X. Yan, Z. Chen, A. Xu, X. Wang, X. Liang, and L. Lin, “Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 9577–9586.
  28. G. Han, Y. He, S. Huang, J. Ma, and S.-F. Chang, “Query adaptive few-shot object detection with heterogeneous graph convolutional networks,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3263–3272.
  29. C. Zhu, F. Chen, U. Ahmed, Z. Shen, and M. Savvides, “Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 8782–8791.
  30. A. Wu, Y. Han, L. Zhu, and Y. Yang, “Universal-prototype enhancing for few-shot object detection,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 9567–9576.
  31. G. Zhang, Z. Luo, K. Cui, S. Lu, and E. P. Xing, “Meta-detr: Image-level few-shot detection with inter-class correlation exploitation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  32. G. Han, J. Ma, S. Huang, L. Chen, and S.-F. Chang, “Few-shot object detection with fully cross-transformer,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 5321–5330.
  33. T. Kong, A. Yao, Y. Chen, and F. Sun, “HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
  34. Z. Li and F. Zhou, “FSSD: Feature Fusion Single Shot Multibox DAetector,” arXiv preprint arXiv:1712.00960, 2017.
  35. Z. Shen, Z. Liu, J. Li, Y.-G. Jiang, Y. Chen, and X. Xue, “DSOD: Learning Deeply Supervised Object Detectors From Scratch,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct 2017.
  36. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  37. https://subtchallenge.com.
Citations (2)
View on Semantic Scholar

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now