Title
Semantically Coherent Out-of-Distribution Detection.
Abstract
Current out-of-distribution (OOD) detection benchmarks are commonly built by defining one dataset as in-distribution (ID) and all others as OOD. However, these benchmarks unfortunately introduce some unwanted and impractical goals, e.g., to perfectly distinguish CIFAR dogs from ImageNet dogs, even though they have the same semantics and negligible covariate shifts. These unrealistic goals will result in an extremely narrow range of model capabilities, greatly limiting their use in real applications. To overcome these drawbacks, we re-design the benchmarks and propose the semantically coherent out-of-distribution detection (SC-OOD). On the SC-OOD benchmarks, existing methods suffer from large performance degradation, suggesting that they are extremely sensitive to low-level discrepancy between data sources while ignoring their inherent semantics. To develop an effective SC-OOD detection approach, we leverage an external unlabeled set and design a concise framework featured by unsupervised dual grouping (UDG) for the joint modeling of ID and OOD data. The proposed UDG can not only enrich the semantic knowledge of the model by exploiting unlabeled data in an unsupervised manner, but also distinguish ID/OOD samples to enhance ID classification and OOD detection tasks simultaneously. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on SC-OOD benchmarks. Code and benchmarks are provided on our project page: https://jingkang50.github.io/projects/scood.
Year
DOI
Venue
2021
10.1109/ICCV48922.2021.00819
ICCV
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Jingkang Yang100.68
Haoqi Wang200.68
Litong Feng39711.26
Xiaopeng Yan433.36
Huabin Zheng501.01
Wayne Zhang600.68
Ziwei Liu700.34