Deep Anomaly Detection with Outlier Exposure
arxiv.org · 7,232 words · saved by 1 readers
N/A
Published as a conference paper at ICLR 2019 D EEP A NOMALY D ETECTION WITH O UTLIER E XPOSURE Dan Hendrycks Mantas Mazeika Thomas Dietterich University of California, Berkeley University of Chicago Oregon State University hendrycks@berkeley.edu mantas@ttic.edu tgd@oregonstate.edu…
saved by
related reading
- Your Out-of-Distribution Detection Method is Not Robust!arxiv.org
- [1706.04599] On Calibration of Modern Neural Networksarxiv.org
- arxiv.org/pdf/1805.08522arxiv.org
- [2009.11732] A Unifying Review of Deep and Shallow Anomaly Detectionarxiv.org
- Understanding deep learning requires rethinking generalizationarxiv.org
- 2409.02908arxiv.org
- [1911.08731] Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationarxiv.org
- Deep Learning is Not So Mysterious or Differentarxiv.org
- On Getting Confidence Estimates from Neural Networks | Bharath's notesbharathpbhat.github.io
- Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetsmathai-iclr.github.io
- [2503.02113] Deep Learning is Not So Mysterious or Differentarxiv.org