Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments
Abstract: In this paper, we address unsupervised domain adaptation under noisy environments, which is more challenging and practical than traditional domain adaptation. In this scenario, the model is prone to overfitting noisy labels, resulting in a more pronounced domain shift and a notable decline in the overall model performance. Previous methods employed prototype methods for domain adaptation on robust feature spaces. However, these approaches struggle to effectively classify classes with similar features under noisy environments. To address this issue, we propose a new method to detect and correct confusing class pair. We first divide classes into easy and hard classes based on the small loss criterion. We then leverage the top-2 predictions for each sample after aligning the source and target domain to find the confusing pair in the hard classes. We apply label correction to the noisy samples within the confusing pair. With the proposed label correction method, we can train our model with more accurate labels. Extensive experiments confirm the effectiveness of our method and demonstrate its favorable performance compared with existing state-of-the-art methods. Our codes are publicly available at https://github.com/Hehxcf/CPC/.
- Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. Advances in neural information processing systems, 23.
- Adversarial-learned loss for domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, volume 34, 3521–3528.
- Domain-adversarial training of neural networks. The journal of machine learning research, 17(1): 2096–2030.
- Domain-Adversarial Training of Neural Networks, 189–209.
- Generative adversarial nets. Advances in neural information processing systems, 27.
- Caltech-256 Object Category Dataset.
- Towards accurate and robust domain adaptation under noisy environments. arXiv preprint arXiv:2004.12529.
- Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning, 1989–1998. Pmlr.
- Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In International conference on machine learning, 2304–2313. PMLR.
- Minimum class confusion for versatile domain adaptation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXI 16, 464–480. Springer.
- Contrastive adaptation network for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4893–4902.
- Self-paced learning for latent variable models. Advances in neural information processing systems, 23.
- Sliced wasserstein discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 10285–10295.
- Learning transferable features with deep adaptation networks. In International conference on machine learning, 97–105. PMLR.
- Conditional adversarial domain adaptation. Advances in neural information processing systems, 31.
- Unsupervised domain adaptation with residual transfer networks. Advances in neural information processing systems, 29.
- Deep multi-modality adversarial networks for unsupervised domain adaptation. IEEE Transactions on Multimedia, 21(9): 2419–2431.
- A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 1345–1359.
- Transferrable prototypical networks for unsupervised domain adaptation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2239–2247.
- Multi-adversarial domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, volume 32.
- Adapting visual category models to new domains. In Computer Vision–ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV 11, 213–226. Springer.
- Maximum classifier discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3723–3732.
- Transferable curriculum for weakly-supervised domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, volume 33, 4951–4958.
- Deep coral: Correlation alignment for deep domain adaptation. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14, 443–450. Springer.
- Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 7167–7176.
- Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474.
- Deep hashing network for unsupervised domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 5018–5027.
- Weighted and class-specific maximum mean discrepancy for unsupervised domain adaptation. IEEE Transactions on Multimedia, 22(9): 2420–2433.
- Bridging theory and algorithm for domain adaptation. In International conference on machine learning, 7404–7413. PMLR.
- Unsupervised open domain recognition by semantic discrepancy minimization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 750–759.
- Uncertainty Modeling for Robust Domain Adaptation Under Noisy Environments. IEEE Transactions on Multimedia, 1–14.
- Deep Unsupervised Convolutional Domain Adaptation. In Proceedings of the 25th ACM international conference on ultimedia.
- Adaptive Feature Swapping for Unsupervised Domain Adaptation. In Proceedings of the 31st ACM International Conference on Multimedia, 7017–7028.
- Seek common ground while reserving differences: A model-agnostic module for noisy domain adaptation. IEEE Transactions on Multimedia, 24: 1020–1030.
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.