Out-of-distribution detection based on subspace projection of high-dimensional features output by the last convolutional layer

arXiv:2405.01662v1 Announce Type: new
Abstract: Out-of-distribution (OOD) detection, crucial for reliable pattern classification, discerns whether a sample originates outside the training distribution. This paper concentrates on the high-dimensional features output by the final convolutional layer, which contain rich image features. Our key idea is to project these high-dimensional features into two specific feature subspaces, leveraging the dimensionality reduction capacity of the network's linear layers, trained with Predefined Evenly-Distribution Class Centroids (PEDCC)-Loss. This involves calculating the cosines of three projection angles …

arxiv convolutional cs.cv detection distribution features layer projection type