Balanced Energy Regularization Loss for Out-of-distribution Detection
This addresses OOD detection challenges in tasks like semantic segmentation and long-tailed classification, offering an incremental improvement over prior methods.
The paper tackles the problem of class imbalance in auxiliary out-of-distribution (OOD) data for OOD detection by proposing a balanced energy regularization loss that uses class-wise prior probabilities to regularize majority classes more heavily, achieving state-of-the-art performance in semantic segmentation and long-tailed image classification.
In the field of out-of-distribution (OOD) detection, a previous method that use auxiliary data as OOD data has shown promising performance. However, the method provides an equal loss to all auxiliary data to differentiate them from inliers. However, based on our observation, in various tasks, there is a general imbalance in the distribution of the auxiliary OOD data across classes. We propose a balanced energy regularization loss that is simple but generally effective for a variety of tasks. Our balanced energy regularization loss utilizes class-wise different prior probabilities for auxiliary data to address the class imbalance in OOD data. The main concept is to regularize auxiliary samples from majority classes, more heavily than those from minority classes. Our approach performs better for OOD detection in semantic segmentation, long-tailed image classification, and image classification than the prior energy regularization loss. Furthermore, our approach achieves state-of-the-art performance in two tasks: OOD detection in semantic segmentation and long-tailed image classification. Code is available at https://github.com/hyunjunChhoi/Balanced_Energy.