RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916149941239808 |
|---|---|
| author | Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre |
| author_facet | Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre |
| contents | Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators. Existing solutions address P1 using class-balanced cross-entropy loss and dice loss and P2 by only predicting edges agreed upon by most annotators. In this paper, we propose RankED, a unified ranking-based approach that addresses both the imbalance problem (P1) and the uncertainty problem (P2). RankED tackles these two problems with two components: One component which ranks positive pixels over negative pixels, and the second which promotes high confidence edge pixels to have more label certainty. We show that RankED outperforms previous studies and sets a new state-of-the-art on NYUD-v2, BSDS500 and Multi-cue datasets. Code is available at https://ranked-cvpr24.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_01795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses Cetinkaya, Bedrettin Kalkan, Sinan Akbas, Emre Computer Vision and Pattern Recognition Detecting edges in images suffers from the problems of (P1) heavy imbalance between positive and negative classes as well as (P2) label uncertainty owing to disagreement between different annotators. Existing solutions address P1 using class-balanced cross-entropy loss and dice loss and P2 by only predicting edges agreed upon by most annotators. In this paper, we propose RankED, a unified ranking-based approach that addresses both the imbalance problem (P1) and the uncertainty problem (P2). RankED tackles these two problems with two components: One component which ranks positive pixels over negative pixels, and the second which promotes high confidence edge pixels to have more label certainty. We show that RankED outperforms previous studies and sets a new state-of-the-art on NYUD-v2, BSDS500 and Multi-cue datasets. Code is available at https://ranked-cvpr24.github.io. |
| title | RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Losses |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.01795 |