Hierarchical Selective Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913635429777408 |
|---|---|
| author | Goren, Shani Galil, Ido El-Yaniv, Ran |
| author_facet | Goren, Shani Galil, Ido El-Yaniv, Ran |
| contents | Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11533 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hierarchical Selective Classification Goren, Shani Galil, Ido El-Yaniv, Ran Machine Learning Computer Vision and Pattern Recognition Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our approach leverages the inherent structure of class relationships, enabling models to reduce the specificity of their predictions when faced with uncertainty. In this paper, we first formalize hierarchical risk and coverage, and introduce hierarchical risk-coverage curves. Next, we develop algorithms for hierarchical selective classification (which we refer to as "inference rules"), and propose an efficient algorithm that guarantees a target accuracy constraint with high probability. Lastly, we conduct extensive empirical studies on over a thousand ImageNet classifiers, revealing that training regimes such as CLIP, pretraining on ImageNet21k and knowledge distillation boost hierarchical selective performance. |
| title | Hierarchical Selective Classification |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.11533 |