pith. sign in

arxiv: 2107.08976 · v2 · pith:74PKCW62new · submitted 2021-07-19 · 💻 cs.CV

OODformer: Out-Of-Distribution Detection Transformer

classification 💻 cs.CV
keywords detectiondataconfidencediscriminateimagemodeloodformerout-of-distribution
0
0 comments X
read the original abstract

A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD) samples. In real-world safety-critical applications, in particular, it is important to be aware if a new data point is OOD. To date, OOD detection is typically addressed using either confidence scores, auto-encoder based reconstruction, or by contrastive learning. However, the global image context has not yet been explored to discriminate the non-local objectness between in-distribution and OOD samples. This paper proposes a first-of-its-kind OOD detection architecture named OODformer that leverages the contextualization capabilities of the transformer. Incorporating the trans\-former as the principal feature extractor allows us to exploit the object concepts and their discriminate attributes along with their co-occurrence via visual attention. Using the contextualised embedding, we demonstrate OOD detection using both class-conditioned latent space similarity and a network confidence score. Our approach shows improved generalizability across various datasets. We have achieved a new state-of-the-art result on CIFAR-10/-100 and ImageNet30.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.