2 citations · 6 across the 5 of their papers we have counts for
5 papers · 1 filter
Revisiting Energy-Based Model for Out-of-Distribution Detection
Yifan Wu, Xichen Ye, Songmin Dai +4
Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution.…
Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
Songmin Dai, Yifan Wu, Xiaoqiang Li +1
Recent unsupervised anomaly detection methods often rely on feature extractors pretrained with auxiliary datasets or on well-crafted anomaly-simulated samples. However, this might…
Reasoning Structural Relation for Occlusion-Robust Facial Landmark Localization
Congcong Zhu, Xiaoqiang Li, Jide Li +2
In facial landmark localization tasks, various occlusions heavily degrade the localization accuracy due to the partial observability of facial features. This paper proposes a struc…
Unsupervised Learning of Multi-level Structures for Anomaly Detection
Songmin Dai, Jide Li, Lu Wang +3
The main difficulty in high-dimensional anomaly detection tasks is the lack of anomalous data for training. And simply collecting anomalous data from the real world, common distrib…
Learning Segmentation Masks with the Independence Prior
Songmin Dai, Xiaoqiang Li, Lu Wang +3
An instance with a bad mask might make a composite image that uses it look fake. This encourages us to learn segmentation by generating realistic composite images. To achieve this,…