Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
Abstract
Due to the intractability of characterizing everything that looks unlike the normal data, anomaly detection (AD) is traditionally treated as an unsupervised problem utilizing only normal samples. However, it has recently been found that unsupervised image AD can be drastically improved through the utilization of huge corpora of random images to represent anomalousness; a technique which is known as Outlier Exposure. In this paper we show that specialized AD learning methods seem unnecessary for state-of-the-art performance, and furthermore one can achieve strong performance with just a small collection of Outlier Exposure data, contradicting common assumptions in the field of AD. We find that standard classifiers and semi-supervised one-class methods trained to discern between normal samples and relatively few random natural images are able to outperform the current state of the art on an established AD benchmark with ImageNet. Further experiments reveal that even one well-chosen outlier sample is sufficient to achieve decent performance on this benchmark (79.3% AUC). We investigate this phenomenon and find that one-class methods are more robust to the choice of training outliers, indicating that there are scenarios where these are still more useful than standard classifiers. Additionally, we include experiments that delineate the scenarios where our results hold. Lastly, no training samples are necessary when one uses the representations learned by CLIP, a recent foundation model, which achieves state-of-the-art AD results on CIFAR-10 and ImageNet in a zero-shot setting.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2022
- DOI:
- 10.48550/arXiv.2205.11474
- arXiv:
- arXiv:2205.11474
- Bibcode:
- 2022arXiv220511474L
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- 47 pages