Papers
Topics
Authors
Recent
2000 character limit reached

Prompt-Driven Feature Diffusion for Open-World Semi-Supervised Learning (2404.11795v1)

Published 17 Apr 2024 in cs.LG, cs.AI, and cs.CV

Abstract: In this paper, we present a novel approach termed Prompt-Driven Feature Diffusion (PDFD) within a semi-supervised learning framework for Open World Semi-Supervised Learning (OW-SSL). At its core, PDFD deploys an efficient feature-level diffusion model with the guidance of class-specific prompts to support discriminative feature representation learning and feature generation, tackling the challenge of the non-availability of labeled data for unseen classes in OW-SSL. In particular, PDFD utilizes class prototypes as prompts in the diffusion model, leveraging their class-discriminative and semantic generalization ability to condition and guide the diffusion process across all the seen and unseen classes. Furthermore, PDFD incorporates a class-conditional adversarial loss for diffusion model training, ensuring that the features generated via the diffusion process can be discriminatively aligned with the class-conditional features of the real data. Additionally, the class prototypes of the unseen classes are computed using only unlabeled instances with confident predictions within a semi-supervised learning framework. We conduct extensive experiments to evaluate the proposed PDFD. The empirical results show PDFD exhibits remarkable performance enhancements over many state-of-the-art existing methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Towards open world recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2015.
  2. Mixmatch: A holistic approach to semi-supervised learning. In Advances in Neural Information Processing Systems (NeurIPS), 2019.
  3. ReMixMatch: Semi-supervised learning with distribution matching and augmentation anchoring. In International Conference on Learning Representations (ICLR), 2020.
  4. Open-world semi-supervised learning. In International Conference on Learning Representations (ICLR), 2022.
  5. A simple framework for contrastive learning of visual representations. In International conference on machine learning (ICML). PMLR, 2020.
  6. Text-to-image diffusion models are zero-shot classifiers. In ICLR 2023 Workshop on Multimodal Representation Learning: Perks and Pitfalls, 2023.
  7. Imagenet: A large-scale hierarchical image database. In conference on computer vision and pattern recognition (CVPR), 2009.
  8. Protodiff: Learning to learn prototypical networks by task-guided diffusion. arXiv preprint arXiv:2306.14770, 2023.
  9. A unified objective for novel class discovery. In International Conference on Computer Vision (ICCV), 2021.
  10. Generative adversarial networks. Advances in Neural Information Processing Systems (NeurIPS), 2014.
  11. Semi-supervised learning by entropy minimization. Advances in neural information processing systems (NeurIPS), 2004.
  12. Safe deep semi-supervised learning for unseen-class unlabeled data. In International Conference on Machine Learning (ICML), 2020.
  13. Robust semi-supervised learning when not all classes have labels. Advances in Neural Information Processing Systems (NeurIPS), 2022.
  14. Automatically discovering and learning new visual categories with ranking statistics. In International Conference on Learning Representations (ICLR), 2019.
  15. Learning to discover novel visual categories via deep transfer clustering. In International Conference on Computer Vision (ICCV), 2019.
  16. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems (NeurIPS), 2020.
  17. Diffusion-ss3d: Diffusion model for semi-supervised 3d object detection. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.
  18. Learning to cluster in order to transfer across domains and tasks. In International Conference on Learning Representations (ICLR), 2018.
  19. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  20. Learning multiple layers of features from tiny images. Technical report, 2009.
  21. Harold W Kuhn. The hungarian method for the assignment problem. Naval research logistics quarterly, 1955.
  22. Temporal ensembling for semi-supervised learning. In International Conference on Learning Representations (ICLR), 2017.
  23. Your diffusion model is secretly a zero-shot classifier. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  24. Calvin Luo. Understanding diffusion models: A unified perspective. arXiv preprint arXiv:2208.11970, 2022.
  25. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784, 2014.
  26. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning (ICML), 2021.
  27. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
  28. Imagenet large scale visual recognition challenge. International journal of computer vision, 2015.
  29. Deep unsupervised learning using nonequilibrium thermodynamics. In International Conference on Machine Learning (ICML), 2015.
  30. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In Advances in Neural Information Processing Systems (NeurIPS), 2020.
  31. Denoising diffusion implicit models. In International Conference on Learning Representations (ICLR), 2021.
  32. Conditional gaussian distribution learning for open set recognition. In Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  33. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In Advances in Neural Information Processing Systems (NeurIPS), 2017.
  34. Diffusion models: A comprehensive survey of methods and applications. ACM Computing Surveys, 2023.
  35. Diffusion models and semi-supervised learners benefit mutually with few labels. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.
  36. Xiaojin Jerry Zhu. Semi-supervised learning literature survey. 2005.

Summary

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

Slide Deck Streamline Icon: https://streamlinehq.com

Whiteboard

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

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

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.