A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf
.
Dense outlier detection and open-set recognition based on training with noisy negative images
[article]
2022
arXiv
pre-print
Deep convolutional models often produce inadequate predictions for inputs foreign to the training distribution. Consequently, the problem of detecting outlier images has recently been receiving a lot of attention. Unlike most previous work, we address this problem in the dense prediction context in order to be able to locate outlier objects in front of in-distribution background. Our approach is based on two reasonable assumptions. First, we assume that the inlier dataset is related to some
arXiv:2101.09193v2
fatcat:zux3txayvzdwpmbmw4rdytnrf4