Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915711707774976 |
|---|---|
| author | Peng, Kunyu Wen, Di Sarfraz, M. Saquib Chen, Yufan Zheng, Junwei Schneider, David Yang, Kailun Wu, Jiamin Roitberg, Alina Stiefelhagen, Rainer |
| author_facet | Peng, Kunyu Wen, Di Sarfraz, M. Saquib Chen, Yufan Zheng, Junwei Schneider, David Yang, Kailun Wu, Jiamin Roitberg, Alina Stiefelhagen, Rainer |
| contents | Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effectively reject them in unseen domains. While the OSDG field has seen considerable advancements, the impact of label noise--a common issue in real-world datasets--has been largely overlooked. Label noise can mislead model optimization, thereby exacerbating the challenges of open-set recognition in novel domains. In this study, we take the first step towards addressing Open-Set Domain Generalization under Noisy Labels (OSDG-NL) by constructing dedicated benchmarks derived from widely used OSDG datasets, including PACS and DigitsDG. We evaluate baseline approaches by integrating techniques from both label denoising and OSDG methodologies, highlighting the limitations of existing strategies in handling label noise effectively. To address these limitations, we propose HyProMeta, a novel framework that integrates hyperbolic category prototypes for label noise-aware meta-learning alongside a learnable new-category agnostic prompt designed to enhance generalization to unseen classes. Our extensive experiments demonstrate the superior performance of HyProMeta compared to state-of-the-art methods across the newly established benchmarks. The source code of this work is released at https://github.com/KPeng9510/HyProMeta. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18342 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization Peng, Kunyu Wen, Di Sarfraz, M. Saquib Chen, Yufan Zheng, Junwei Schneider, David Yang, Kailun Wu, Jiamin Roitberg, Alina Stiefelhagen, Rainer Computer Vision and Pattern Recognition Machine Learning Image and Video Processing Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effectively reject them in unseen domains. While the OSDG field has seen considerable advancements, the impact of label noise--a common issue in real-world datasets--has been largely overlooked. Label noise can mislead model optimization, thereby exacerbating the challenges of open-set recognition in novel domains. In this study, we take the first step towards addressing Open-Set Domain Generalization under Noisy Labels (OSDG-NL) by constructing dedicated benchmarks derived from widely used OSDG datasets, including PACS and DigitsDG. We evaluate baseline approaches by integrating techniques from both label denoising and OSDG methodologies, highlighting the limitations of existing strategies in handling label noise effectively. To address these limitations, we propose HyProMeta, a novel framework that integrates hyperbolic category prototypes for label noise-aware meta-learning alongside a learnable new-category agnostic prompt designed to enhance generalization to unseen classes. Our extensive experiments demonstrate the superior performance of HyProMeta compared to state-of-the-art methods across the newly established benchmarks. The source code of this work is released at https://github.com/KPeng9510/HyProMeta. |
| title | Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization |
| topic | Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2412.18342 |