How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

Authors: Xuefeng Du, Zhen Fang, Ilias Diakonikolas, Yixuan Li

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, SAL achieves state-of-the-art performance on common benchmarks, reinforcing our theoretical insights.
Researcher Affiliation Academia 1Department of Computer Sciences, University of Wisconsin-Madison 2Australian Artificial Intelligence Institute, University of Technology Sydney
Pseudocode Yes A pseudo algorithm of SAL is in Appendix (see Algorithm 1).
Open Source Code Yes Code is publicly available at https://github.com/deeplearning-wisc/sal.
Open Datasets Yes WOODS considered CIFAR-10 and CIFAR-100 (Krizhevsky et al., 2009) as ID datasets (Pin).
Dataset Splits No The paper mentions splitting CIFAR datasets into two halves for ID training and wild mixture creation but does not explicitly specify a validation dataset split.
Hardware Specification Yes We run all experiments with Python 3.8.5 and Py Torch 1.13.1, using NVIDIA Ge Force RTX 2080Ti GPUs.
Software Dependencies Yes We run all experiments with Python 3.8.5 and Py Torch 1.13.1, using NVIDIA Ge Force RTX 2080Ti GPUs.
Experiment Setup Yes We train the ID classifier hw using stochastic gradient descent with a momentum of 0.9, weight decay of 0.0005, and an initial learning rate of 0.1. We train for 100 epochs using cosine learning rate decay, a batch size of 128, and a dropout rate of 0.3.