https://github.com/max-andr/relu_networks_overconfident
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]
https://github.com/max-andr/relu_networks_overconfident
Last synced: 5 months ago
JSON representation
Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem [CVPR 2019, oral]
- Host: GitHub
- URL: https://github.com/max-andr/relu_networks_overconfident
- Owner: max-andr
- Created: 2019-04-05T19:48:12.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2019-07-14T13:05:58.000Z (almost 7 years ago)
- Last Synced: 2024-07-24T04:36:31.613Z (over 1 year ago)
- Language: Python
- Homepage: https://arxiv.org/abs/1812.05720
- Size: 201 MB
- Stars: 181
- Watchers: 7
- Forks: 21
- Open Issues: 0
Awesome Lists containing this project
- awesome-computer-vision-papers - 2019CVPR