SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2306.03715 · ICML · 2023

Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability

Bo Han, Jianing Zhu, Tongliang Liu, Jiangchao Yao, Jianliang Xu, Hengzhuang Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 2 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.

RepositoryRoleRan
tmlr-group/unleashing-mask canonical 2 of 7
FunctionStatusWhere it lives
fpr_and_fdr_at_recall Ran tmlr-group/unleashing-mask/utils/get_scores.py
code served (permissive licence) · get_code("3853ecdb6fc74451")
stable_cumsum Ran tmlr-group/unleashing-mask/utils/get_scores.py
code served (permissive licence) · get_code("d4acb3120a027622")
accumulate Not yet run tmlr-group/unleashing-mask/utils/net_utils.py
code served (permissive licence) · get_code("8a42a6951b0c5e57")
arg_to_varname Not yet run tmlr-group/unleashing-mask/configs/parser.py
code served (permissive licence) · get_code("177a4abf40724f6e")
argv_to_vars Not yet run tmlr-group/unleashing-mask/configs/parser.py
code served (permissive licence) · get_code("ffc9d7cced6f71fb")
get_lr Not yet run tmlr-group/unleashing-mask/utils/net_utils.py
code served (permissive licence) · get_code("717f5458343a0b63")
trim_preceding_hyphens Not yet run tmlr-group/unleashing-mask/configs/parser.py
code served (permissive licence) · get_code("a99f170ebd682af5")

Repositories linked to this paper

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 an indispensable aspect of secure AI when deploying machine learning models in real-world applications. Previous paradigms either explore better scoring functions or utilize the knowledge of outliers to equip the models with the ability of OOD detection. However, few of them pay attention to the intrinsic OOD detection capability of the given model. In this work, we generally discover the existence of an intermediate stage of a model trained on in-distribution (ID) data having higher OOD detection performance than that of its final stage across different settings, and further identify one critical data-level attribution to be learning with the atypical samples. Based on such insights, we propose a novel method, Unleashing Mask, which aims to restore the OOD discriminative capabilities of the well-trained model with ID data. Our method utilizes a mask to figure out the memorized atypical samples, and then finetune the model or prune it with the introduced mask to forget them. Extensive experiments and analysis demonstrate the effectiveness of our method. The code is available at: https://github.com/ tmlr-group/Unleashing-Mask.

For agents

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

get_harvested_code_for_paper("2306.03715")
get_code_for_paper("2306.03715")
have("2306.03715")

Connect an agent — have() is free.