RG: OUT-OF-DISTRIBUTION DETECTION WITH REACTIVATE GRADNORM

Mingyu Xu, Kexin Wang, Zheng Lian, Licai Sun, Bin Liu, Jianhua Tao

Keywords: OOD detection, Uncertainty Learning

TL;DR: The information of joint feature space and output space improves the performance of OOD detection.

Abstract: Detecting out-of-distribution (OOD) data is critical to building reliable machine learning systems in the open world. Previous works mainly perform OOD detection in feature space or output space. Recently, researchers have achieved promising results using gradient information, which combines the information in both feature and output space for OOD detection. However, existing works still suffer from the problem of overconfidence. To address this problem, we propose a novel method called ``Reactivate Gradnorm (RG)'', which exploits the norm of the clipped feature vector and the energy in the output space for OOD detection. To verify the effectiveness of our method, we conduct experiments on four benchmark datasets. Experimental results demonstrate that our RG outperforms existing state-of-the-art approaches by 2.06\% in average AUROC. Meanwhile, RG is easy to implement and does not require additional OOD data or fine-tuning process. We can realize OOD detection in only one forward pass of any pretrained model.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: General Machine Learning (ie none of the above)