Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2601.22703 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911615932170240 |
|---|---|
| author | Hassan, Abid Ngo, Tuan Shafiq, Saad Medvidovic, Nenad |
| author_facet | Hassan, Abid Ngo, Tuan Shafiq, Saad Medvidovic, Nenad |
| contents | Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc detection methods operate on penultimate feature representations derived from global average pooling (GAP) -- a lossy operation that discards valuable distributional statistics from activation maps prior to global average pooling. We contend that these overlooked statistics, particularly channel-wise variance and dominant (maximum) activations, are highly discriminative for OOD detection. We introduce DAVIS, a simple and broadly applicable post-hoc technique that enriches feature vectors by incorporating these crucial statistics, directly addressing the information loss from GAP. Extensive evaluations show DAVIS sets a new benchmark across diverse architectures, including ResNet, DenseNet, and EfficientNet. It achieves significant reductions in the false positive rate (FPR95), with improvements of 48.26\% on CIFAR-10 using ResNet-18, 38.13\% on CIFAR-100 using ResNet-34, and 26.83\% on ImageNet-1k benchmarks using MobileNet-v2. Our analysis reveals the underlying mechanism for this improvement, providing a principled basis for moving beyond the mean in OOD detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22703 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation Hassan, Abid Ngo, Tuan Shafiq, Saad Medvidovic, Nenad Computer Vision and Pattern Recognition Detecting out-of-distribution (OOD) inputs is a critical safeguard for deploying machine learning models in the real world. However, most post-hoc detection methods operate on penultimate feature representations derived from global average pooling (GAP) -- a lossy operation that discards valuable distributional statistics from activation maps prior to global average pooling. We contend that these overlooked statistics, particularly channel-wise variance and dominant (maximum) activations, are highly discriminative for OOD detection. We introduce DAVIS, a simple and broadly applicable post-hoc technique that enriches feature vectors by incorporating these crucial statistics, directly addressing the information loss from GAP. Extensive evaluations show DAVIS sets a new benchmark across diverse architectures, including ResNet, DenseNet, and EfficientNet. It achieves significant reductions in the false positive rate (FPR95), with improvements of 48.26\% on CIFAR-10 using ResNet-18, 38.13\% on CIFAR-100 using ResNet-34, and 26.83\% on ImageNet-1k benchmarks using MobileNet-v2. Our analysis reveals the underlying mechanism for this improvement, providing a principled basis for moving beyond the mean in OOD detection. |
| title | DAVIS: OOD Detection via Dominant Activations and Variance for Increased Separation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.22703 |