A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912961072726016 |
|---|---|
| author | Genç, Furkan Özdemir, Onat Akbaş, Emre |
| author_facet | Genç, Furkan Özdemir, Onat Akbaş, Emre |
| contents | Out-of-distribution (OOD) detection is critical in safety-sensitive applications. While this challenge has been addressed from various perspectives, the influence of training objectives on OOD behavior remains comparatively underexplored. In this paper, we present a systematic comparison of four widely used training objectives: Cross-Entropy Loss, Prototype Loss, Triplet Loss, and Average Precision (AP) Loss, spanning probabilistic, prototype-based, metric-learning, and ranking-based supervision, for OOD detection in image classification under standardized OpenOOD protocols. Across CIFAR-10/100 and ImageNet-200, we find that Cross-Entropy Loss, Prototype Loss, and AP Loss achieve comparable in-distribution accuracy, while Cross-Entropy Loss provides the most consistent near- and far-OOD performance overall; the other objectives can be competitive in specific settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07571 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification Genç, Furkan Özdemir, Onat Akbaş, Emre Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Out-of-distribution (OOD) detection is critical in safety-sensitive applications. While this challenge has been addressed from various perspectives, the influence of training objectives on OOD behavior remains comparatively underexplored. In this paper, we present a systematic comparison of four widely used training objectives: Cross-Entropy Loss, Prototype Loss, Triplet Loss, and Average Precision (AP) Loss, spanning probabilistic, prototype-based, metric-learning, and ranking-based supervision, for OOD detection in image classification under standardized OpenOOD protocols. Across CIFAR-10/100 and ImageNet-200, we find that Cross-Entropy Loss, Prototype Loss, and AP Loss achieve comparable in-distribution accuracy, while Cross-Entropy Loss provides the most consistent near- and far-OOD performance overall; the other objectives can be competitive in specific settings. |
| title | A Systematic Comparison of Training Objectives for Out-of-Distribution Detection in Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.07571 |