Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
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_ | 1866929570013249536 |
|---|---|
| author | Liu, Kai Fu, Zhihang Jin, Sheng Chen, Chao Chen, Ze Jiang, Rongxin Zhou, Fan Chen, Yaowu Ye, Jieping |
| author_facet | Liu, Kai Fu, Zhihang Jin, Sheng Chen, Chao Chen, Ze Jiang, Rongxin Zhou, Fan Chen, Yaowu Ye, Jieping |
| contents | Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy of existing OOD detection methods is often impeded by the inherent imbalance of in-distribution (ID) data, which causes significant performance decline. Through statistical observations, we have identified two common challenges faced by different OOD detectors: misidentifying tail class ID samples as OOD, while erroneously predicting OOD samples as head class from ID. To explain this phenomenon, we introduce a generalized statistical framework, termed ImOOD, to formulate the OOD detection problem on imbalanced data distribution. Consequently, the theoretical analysis reveals that there exists a class-aware bias item between balanced and imbalanced OOD detection, which contributes to the performance gap. Building upon this finding, we present a unified training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs. Our theoretically grounded method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks against several state-of-the-art OOD detection approaches. Code is available at https://github.com/alibaba/imood. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution Liu, Kai Fu, Zhihang Jin, Sheng Chen, Chao Chen, Ze Jiang, Rongxin Zhou, Fan Chen, Yaowu Ye, Jieping Computer Vision and Pattern Recognition Detecting and rejecting unknown out-of-distribution (OOD) samples is critical for deployed neural networks to void unreliable predictions. In real-world scenarios, however, the efficacy of existing OOD detection methods is often impeded by the inherent imbalance of in-distribution (ID) data, which causes significant performance decline. Through statistical observations, we have identified two common challenges faced by different OOD detectors: misidentifying tail class ID samples as OOD, while erroneously predicting OOD samples as head class from ID. To explain this phenomenon, we introduce a generalized statistical framework, termed ImOOD, to formulate the OOD detection problem on imbalanced data distribution. Consequently, the theoretical analysis reveals that there exists a class-aware bias item between balanced and imbalanced OOD detection, which contributes to the performance gap. Building upon this finding, we present a unified training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs. Our theoretically grounded method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks against several state-of-the-art OOD detection approaches. Code is available at https://github.com/alibaba/imood. |
| title | Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.16430 |