Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Entropic Open-set Active Learning (2312.14126v1)

Published 21 Dec 2023 in cs.CV

Abstract: Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data. Despite impressive performance in closed-set settings, most AL methods fail in real-world scenarios where the unlabeled data contains unknown categories. Recently, a few studies have attempted to tackle the AL problem for the open-set setting. However, these methods focus more on selecting known samples and do not efficiently utilize unknown samples obtained during AL rounds. In this work, we propose an Entropic Open-set AL (EOAL) framework which leverages both known and unknown distributions effectively to select informative samples during AL rounds. Specifically, our approach employs two different entropy scores. One measures the uncertainty of a sample with respect to the known-class distributions. The other measures the uncertainty of the sample with respect to the unknown-class distributions. By utilizing these two entropy scores we effectively separate the known and unknown samples from the unlabeled data resulting in better sampling. Through extensive experiments, we show that the proposed method outperforms existing state-of-the-art methods on CIFAR-10, CIFAR-100, and TinyImageNet datasets. Code is available at \url{https://github.com/bardisafa/EOAL}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Deep batch active learning by diverse, uncertain gradient lower bounds. arXiv preprint arXiv:1906.03671.
  2. Margin based active learning. In Learning Theory: 20th Annual Conference on Learning Theory, COLT 2007, San Diego, CA, USA; June 13-15, 2007. Proceedings 20, 35–50. Springer.
  3. Towards open set deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1563–1572.
  4. Learning open set network with discriminative reciprocal points. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part III 16, 507–522. Springer.
  5. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4): 834–848.
  6. Unified Classification and Rejection: A One-versus-All Framework. arXiv preprint arXiv:2311.13355.
  7. Contrastive coding for active learning under class distribution mismatch. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 8927–8936.
  8. Generative openmax for multi-class open set classification. arXiv preprint arXiv:1707.07418.
  9. Generative adversarial nets. Advances in neural information processing systems, 27.
  10. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
  11. Active learning by query by committee with robust divergences. Information Geometry, 1–26.
  12. Segment anything. arXiv preprint arXiv:2304.02643.
  13. Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. Advances in neural information processing systems, 32.
  14. Similar: Submodular information measures based active learning in realistic scenarios. Advances in Neural Information Processing Systems, 34: 18685–18697.
  15. Learning multiple layers of features from tiny images. Technical Report TR-2009, University of Toronto.
  16. Pmal: Open set recognition via robust prototype mining. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 1872–1880.
  17. Latent Structured Active Learning. In Burges, C.; Bottou, L.; Welling, M.; Ghahramani, Z.; and Weinberger, K., eds., Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc.
  18. MacQueen, J.; et al. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, 281–297. Oakland, CA, USA.
  19. Class anchor clustering: A loss for distance-based open set recognition. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 3570–3578.
  20. Difficulty-aware simulator for open set recognition. In European Conference on Computer Vision, 365–381. Springer.
  21. Open Set Learning with Counterfactual Images. In Proceedings of the European Conference on Computer Vision (ECCV).
  22. Active learning using pre-clustering. In Proceedings of the twenty-first international conference on Machine learning, 79.
  23. Active learning for open-set annotation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 41–49.
  24. C2ae: Class conditioned auto-encoder for open-set recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2307–2316.
  25. Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning. Advances in Neural Information Processing Systems, 35: 31416–31429.
  26. Active learning by feature mixing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 12237–12246.
  27. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
  28. Learning transferable visual models from natural language supervision. In International conference on machine learning, 8748–8763. PMLR.
  29. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 779–788.
  30. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, 28.
  31. Ruder, S. 2016. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747.
  32. Open-Set Automatic Target Recognition. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1–5. IEEE.
  33. Ovanet: One-vs-all network for universal domain adaptation. In Proceedings of the ieee/cvf international conference on computer vision, 9000–9009.
  34. Efficient parameter-free clustering using first neighbor relations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 8934–8943.
  35. Toward open set recognition. IEEE transactions on pattern analysis and machine intelligence, 35(7): 1757–1772.
  36. Active learning for convolutional neural networks: A core-set approach. arXiv preprint arXiv:1708.00489.
  37. Query by committee. In Proceedings of the fifth annual workshop on Computational learning theory, 287–294.
  38. P-odn: Prototype-based open deep network for open set recognition. Scientific reports, 10(1): 7146.
  39. Sohn, K. 2016. Improved deep metric learning with multi-class n-pair loss objective. Advances in neural information processing systems, 29.
  40. Conditional gaussian distribution learning for open set recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 13480–13489.
  41. Bayesian generative active deep learning. In International Conference on Machine Learning, 6295–6304. PMLR.
  42. Towards online domain adaptive object detection. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 478–488.
  43. Mixture of Teacher Experts for Source-Free Domain Adaptive Object Detection. In 2022 IEEE International Conference on Image Processing (ICIP), 3606–3610. IEEE.
  44. Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 23539–23549.
  45. A new active labeling method for deep learning. 2014 International Joint Conference on Neural Networks (IJCNN), 112–119.
  46. Submodularity in data subset selection and active learning. In International conference on machine learning, 1954–1963. PMLR.
  47. Representative sampling for text classification using support vector machines. In Advances in Information Retrieval: 25th European Conference on IR Research, ECIR 2003, Pisa, Italy, April 14–16, 2003. Proceedings 25, 393–407. Springer.
  48. Convolutional prototype network for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(5): 2358–2370.
  49. Tiny imagenet classification with convolutional neural networks. CS 231N, 2(5): 8.
  50. Classification-reconstruction learning for open-set recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 4016–4025.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Bardia Safaei (10 papers)
  2. Vibashan VS (22 papers)
  3. Vishal M. Patel (230 papers)
  4. Celso M. De Melo (16 papers)
Citations (11)
View on Semantic Scholar

Summary

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

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

GitHub

  1. GitHub - bardisafa/EOAL: [AAAI 2024] An Implementation of Entropic Open-set Active Learning (18 stars)