Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911361606352896 |
|---|---|
| author | Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo |
| author_facet | Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo |
| contents | Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmark results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_19486 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation Garg, Arpit Nguyen, Cuong Felix, Rafael Do, Thanh-Toan Carneiro, Gustavo Computer Vision and Pattern Recognition Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmark results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases. |
| title | Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2305.19486 |