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

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

6 Jun 2023arXiv:2306.03715archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.03715")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it.

By repository: official repository: 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tmlr-group/unleashing-mask officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 2 ran; 1 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · fixture could not drive it
5unverified

Licence: 0 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tmlr-group/unleashing-mask. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

fpr_and_fdr_at_recall tmlr-group/unleashing-mask/utils/get_scores.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3853ecdb6fc74451 · report
stable_cumsum tmlr-group/unleashing-mask/utils/get_scores.py official repository ran · honoured contract fingerprinted MIT (permissive) · d4acb3120a027622 · report
accumulate tmlr-group/unleashing-mask/utils/net_utils.py official repository unverified MIT (permissive) · 8a42a6951b0c5e57 · report
arg_to_varname tmlr-group/unleashing-mask/configs/parser.py official repository unverified MIT (permissive) · 177a4abf40724f6e · report
argv_to_vars tmlr-group/unleashing-mask/configs/parser.py official repository unverified MIT (permissive) · ffc9d7cced6f71fb · report
get_lr tmlr-group/unleashing-mask/utils/net_utils.py official repository unverified MIT (permissive) · 717f5458343a0b63 · report
trim_preceding_hyphens tmlr-group/unleashing-mask/configs/parser.py official repository unverified MIT (permissive) · a99f170ebd682af5 · report

Tasks

Out-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) ODIN+UMAP (ResNet-50) AUROC 89.24 #12 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) ODIN+UMAP (ResNet-50) FPR95 40.94 #12 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places ODIN+UMAP (ResNet-50) AUROC 86.99 #15 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places ODIN+UMAP (ResNet-50) FPR95 50.06 #15 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN ODIN+UMAP (ResNet-50) AUROC 86.92 #16 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN ODIN+UMAP (ResNet-50) FPR95 49.69 #16 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures ODIN+UMAP (ResNet-50) AUROC 88.35 #22 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures ODIN+UMAP (ResNet-50) FPR95 42.02 #22 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist ODIN+UMAP (ResNet-50) AUROC 94.71 #17 of 28 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist ODIN+UMAP (ResNet-50) FPR95 21.97 #17 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections