Timezone: »
Classifiers used in the wild, in particular for safety-critical systems, should know when they don’t know, in particular make low confidence predictions far away from the train- ing data. We show that ReLU type neural networks fail in this regard as they produce almost always high confidence predictions far away from the training data. For bounded domains we propose a new robust optimization technique similar to adversarial training which enforces low confidence pre- dictions far away from the training data. We show that this technique is surprisingly effective in reducing the confidence of predictions far away from the training data while maintaining high confidence predictions and test error on the original classification task com- pared to standard training. This is a short version of the corresponding CVPR paper.
Author Information
Maksym Andriushchenko (Saarland / Tübingen University)
More from the Same Authors
-
2022 Poster: Towards Understanding Sharpness-Aware Minimization »
Maksym Andriushchenko · Nicolas Flammarion -
2022 Spotlight: Towards Understanding Sharpness-Aware Minimization »
Maksym Andriushchenko · Nicolas Flammarion -
2019 : Spotlight »
Tyler Scott · Kiran Koshy · Jonathan Aigrain · Rene Bidart · Priyadarshini Panda · Dian Ang Yap · Yaniv Yacoby · Raphael Gontijo Lopes · Alberto Marchisio · Erik Englesson · Wanqian Yang · Moritz Graule · Yi Sun · Daniel Kang · Mike Dusenberry · Min Du · Hartmut Maennel · Kunal Menda · Vineet Edupuganti · Luke Metz · David Stutz · Vignesh Srinivasan · Timo Sämann · Vineeth N Balasubramanian · Sina Mohseni · Rob Cornish · Judith Butepage · Zhangyang Wang · Bai Li · Bo Han · Honglin Li · Maksym Andriushchenko · Lukas Ruff · Meet P. Vadera · Yaniv Ovadia · Sunil Thulasidasan · Disi Ji · Gang Niu · Saeed Mahloujifar · Aviral Kumar · SANGHYUK CHUN · Dong Yin · Joyce Xu Xu · Hugo Gomes · Raanan Rohekar