Outlier Synthesis via Hamiltonian Monte Carlo for Out-of-Distribution Detection

Monte Carlo, Hengzhuang Li, Teng Zhang, Sample Midpoint, Discernment Hamiltonian

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• fir-lat/hamos_ood — marked official in Papers with Code; named in the paper
• Fir-lat/HamOS_OOD

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS. Our code is available at: https://github.com/Fir-lat/HamOS_OOD.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.16718")
get_code_for_paper("2501.16718")
have("2501.16718")

Connect an agent — have() is free.