Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 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

Transferability Metrics for Object Detection (2306.15306v1)

Published 27 Jun 2023 in cs.CV

Abstract: Transfer learning aims to make the most of existing pre-trained models to achieve better performance on a new task in limited data scenarios. However, it is unclear which models will perform best on which task, and it is prohibitively expensive to try all possible combinations. If transferability estimation offers a computation-efficient approach to evaluate the generalisation ability of models, prior works focused exclusively on classification settings. To overcome this limitation, we extend transferability metrics to object detection. We design a simple method to extract local features corresponding to each object within an image using ROI-Align. We also introduce TLogME, a transferability metric taking into account the coordinates regression task. In our experiments, we compare TLogME to state-of-the-art metrics in the estimation of transfer performance of the Faster-RCNN object detector. We evaluate all metrics on source and target selection tasks, for real and synthetic datasets, and with different backbone architectures. We show that, over different tasks, TLogME using the local extraction method provides a robust correlation with transfer performance and outperforms other transferability metrics on local and global level features.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Task2vec: Task embedding for meta-learning. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6430–6439, 2019.
  2. Geometric dataset distances via optimal transport. Advances in Neural Information Processing Systems, 33:21428–21439, 2020.
  3. An information-theoretic approach to transferability in task transfer learning. In 2019 IEEE International Conference on Image Processing (ICIP), pages 2309–2313. IEEE, 2019.
  4. Analysis of representations for domain adaptation. Advances in neural information processing systems, 19, 2006.
  5. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
  6. Deep learning for classical japanese literature. arXiv preprint arXiv:1812.01718, 2018.
  7. Emnist: Extending mnist to handwritten letters. In 2017 international joint conference on neural networks (IJCNN), pages 2921–2926. IEEE, 2017.
  8. Large scale fine-grained categorization and domain-specific transfer learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4109–4118, 2018.
  9. Global wheat head detection (gwhd) dataset: a large and diverse dataset of high-resolution rgb-labelled images to develop and benchmark wheat head detection methods. Plant Phenomics, 2020, 2020.
  10. Representation similarity analysis for efficient task taxonomy & transfer learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12387–12396, 2019.
  11. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2):303–338, June 2010.
  12. Tanda: Transfer and adapt pre-trained transformer models for answer sentence selection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 7780–7788, 2020.
  13. A kernel two-sample test. The Journal of Machine Learning Research, 13(1):723–773, 2012.
  14. Don’t stop pretraining: Adapt language models to domains and tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8342–8360, 2020.
  15. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  16. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
  17. Frustratingly easy transferability estimation. In International Conference on Machine Learning, pages 9201–9225. PMLR, 2022.
  18. Jonathan J. Hull. A database for handwritten text recognition research. IEEE Transactions on pattern analysis and machine intelligence, 16(5):550–554, 1994.
  19. Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance. In NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications, 2021.
  20. The open images dataset v4. International Journal of Computer Vision, 128(7):1956–1981, 2020.
  21. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
  22. Ranking neural checkpoints. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2663–2673, 2021.
  23. Benchmarking detection transfer learning with vision transformers. arXiv preprint arXiv:2111.11429, 2021.
  24. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
  25. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017.
  26. Swin transformer: Hierarchical vision transformer using shifted windows. pages 10012–10022, 2021.
  27. Torchvision the machine-vision package of torch. In Proceedings of the 18th ACM international conference on Multimedia, pages 1485–1488, 2010.
  28. Leep: A new measure to evaluate transferability of learned representations. In International Conference on Machine Learning, pages 7294–7305. PMLR, 2020.
  29. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  30. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016.
  31. Faster r-cnn: Towards real-time object detection with region proposal networks. volume 28, 2015.
  32. Shenggan. Bccd dataset, 2017.
  33. Depara: Deep attribution graph for deep knowledge transferability. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3922–3930, 2020.
  34. Otce: A transferability metric for cross-domain cross-task representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15779–15788, 2021.
  35. Learning to learn: Introduction and overview. In Learning to learn, pages 3–17. Springer, 1998.
  36. Transferability and hardness of supervised classification tasks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1395–1405, 2019.
  37. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.
  38. Explicit inductive bias for transfer learning with convolutional networks. In International Conference on Machine Learning, pages 2825–2834. PMLR, 2018.
  39. How transferable are features in deep neural networks? volume 27, 2014.
  40. Logme: Practical assessment of pre-trained models for transfer learning. In International Conference on Machine Learning, pages 12133–12143. PMLR, 2021.
  41. A survey of modern deep learning based object detection models. Digital Signal Processing, page 103514, 2022.
  42. Taskonomy: Disentangling task transfer learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3712–3722, 2018.
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