Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.10094 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917841131798528 |
|---|---|
| author | Fang, Kun Tao, Qinghua Yang, Zuopeng Huang, Xiaolin Yang, Jie |
| author_facet | Fang, Kun Tao, Qinghua Yang, Zuopeng Huang, Xiaolin Yang, Jie |
| contents | Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD detection by using the perceptual distances between the given image and its DM generation. DM-based methods bring fresh insights to the field, yet remain under-explored.
In this work, we point out two main limitations in DM-based OoD detection methods: (i) the perceptual metrics on the disparities between the given sample and its generation are devised only at human-perceived levels, ignoring the abstract or high-level patterns that help better reflect the intrinsic disparities in distribution; (ii) only the raw image contents are taken to measure the disparities, while other representations, i.e., the features and probabilities from the classifier-under-protection, are easy to access at hand but are ignored. To this end, our proposed detection framework goes beyond the perceptual distances and looks into the deep representations from the classifier-under-protection with our novel metrics devised correspondingly, leading to more informative disparity assessments between InD and OoD. An anomaly-removal strategy is integrated to remove the abnormal OoD information in the generation, further enhancing the distinctiveness of disparities. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10094 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models Fang, Kun Tao, Qinghua Yang, Zuopeng Huang, Xiaolin Yang, Jie Computer Vision and Pattern Recognition Machine Learning Out-of-Distribution (OoD) detection aims to justify whether a given sample is from the training distribution of the classifier-under-protection, i.e., In-Distribution (InD), or from OoD. Diffusion Models (DMs) are recently utilized in OoD detection by using the perceptual distances between the given image and its DM generation. DM-based methods bring fresh insights to the field, yet remain under-explored. In this work, we point out two main limitations in DM-based OoD detection methods: (i) the perceptual metrics on the disparities between the given sample and its generation are devised only at human-perceived levels, ignoring the abstract or high-level patterns that help better reflect the intrinsic disparities in distribution; (ii) only the raw image contents are taken to measure the disparities, while other representations, i.e., the features and probabilities from the classifier-under-protection, are easy to access at hand but are ignored. To this end, our proposed detection framework goes beyond the perceptual distances and looks into the deep representations from the classifier-under-protection with our novel metrics devised correspondingly, leading to more informative disparity assessments between InD and OoD. An anomaly-removal strategy is integrated to remove the abnormal OoD information in the generation, further enhancing the distinctiveness of disparities. Our work has demonstrated state-of-the-art detection performances among DM-based methods in extensive experiments. |
| title | Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion Models |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.10094 |