Papers › Asymmetric Loss For Multi-Label Classification

Asymmetric Loss For Multi-Label Classification

29 Sep 2020ICCV 2021 10arXiv:2009.14119archive 2025-07-28

Emanuel Ben-Baruch, Tal Ridnik, Nadav Zamir, Asaf Noy, Itamar Friedman, Matan Protter, Lihi Zelnik-Manor

In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during training, resulting in poor accuracy. In this paper, we introduce a novel asymmetric loss ("ASL"), which operates differently on positive and negative samples. The loss enables to dynamically down-weights and hard-thresholds easy negative samples, while also discarding possibly mislabeled samples. We demonstrate how ASL can balance the probabilities of different samples, and how this balancing is translated to better mAP scores. With ASL, we reach state-of-the-art results on multiple popular multi-label datasets: MS-COCO, Pascal-VOC, NUS-WIDE and Open Images. We also demonstrate ASL applicability for other tasks, such as single-label classification and object detection. ASL is effective, easy to implement, and does not increase the training time or complexity. Implementation is available at: https://github.com/Alibaba-MIIL/ASL.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (Alibaba-MIIL/ASL) is linked to this paper; the 12 samples below come from 2 community repositories. Syntology harvested code from Alibaba-MIIL/ASL for another paper.

Alibaba-MIIL/ASL: Syntology's graph links these samples to CVF open access id Ridnik_Asymmetric_Loss_for_Multi-Label_Classification_ICCV_2021_paper (that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 2 repositories, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Alibaba-MIIL/ASL officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CVF open access id Ridnik_Asymmetric_Loss_for_Multi-Label_Classification_ICCV_2021_paper (that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Alibaba-MIIL/TResNet mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
SlongLiu/ASL_reproduce mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (3 instrument-failed) · 1 unverified report
kalelpark/ral mentioned on GitHubpytorchSyntology: not harvested report
mrT23/TResNet mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 4 ran (1 instrument-failed) · 1 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
1ran; the contract check could not run
6ran
2unverified

Licence: 9 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

SlongLiu/ASL_reproduce community (archive-listed) 7 samples, 6 ran (3 instrument-failed) · 1 unverified
average_precision in 38 papers src/helper_functions/helper_functions.py ran; the contract check could not run (RAISES) fingerprinted MIT recorded; this copy not marked cleared · pointer only · f52b226226096fdd · report fixture: signature output:ndarray/1/float, target:ndarray/1/int · returned float64 · level recorded 2026-09-22
conv2d in 119 papers src/models/tresnet/tresnet.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · ad1cabd96edaffc7 · report fixture: signature ni:int/0/int, nf:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
mAP in 7 papers src/helper_functions/helper_functions.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 0759c5625039d127 · report fixture: signature targs:ndarray/2/float, preds:ndarray/2/float · returned float64 · level recorded 2026-09-25
parse_args in 355 papers src/helper_functions/helper_functions.py ran · our draft was wrong MIT recorded; this copy not marked cleared · pointer only · 044fe3f67aac5e39 · report fixture: signature parser:MockParser/0/? · returned Namespace · level recorded 2026-09-24
setup_logger in 122 papers src/helper_functions/logger.py ran MIT recorded; this copy not marked cleared · pointer only · 55faa58ee2b0d1b7 · report fixture: signature output:str/0/str, distributed_rank:int/0/int, color:bool/0/bool, name:str/0/str, abbrev_name:str/0/str · returned Logger · level recorded 2026-09-24
str_to_list in 10 papers src/helper_functions/nuswide_asl.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 50a335a67cb29af0 · report fixture: signature text:str/0/str · returned list · level recorded 2026-09-24
create_model in 163 papers src/models/utils/factory.py unverified MIT recorded; this copy not marked cleared · pointer only · f046cb82f2f2f60a · report
mrT23/TResNet community (archive-listed) 5 samples, 4 ran (1 instrument-failed) · 1 unverified
conv3x3 in 1,376 papers src/models/tresnet_v2/tresnet_v2.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3_depth src/models/tresnet_v2/tresnet_v2.py ran Apache-2.0 (permissive) · 92502509d71ac473 · report fixture: signature planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-25
create_dataloader in 35 papers src/helper_functions/helper_functions.py ran Apache-2.0 (permissive) · df7d18ef933d037a · report fixture: signature args:Args/0/? · returned DataLoader · level recorded 2026-09-25
validate in 313 papers src/helper_functions/helper_functions.py ran Apache-2.0 (permissive) · db31998e52bea4c8 · report fixture: signature model:callable/0/?, val_loader:list/1/tuple · returned AverageMeter · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
src/helper_functions/helper_functions.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 4d3faaaa1c706b0b · report

Tasks

ClassificationGeneral ClassificationImage ClassificationMUlTI-LABEL-ClASSIFICATIONMulti-Label ClassificationObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO TResNet-XL (resolution 640) mAP 88.4 #15 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO TResNet-L (resolution 448) mAP 86.6 #20 of 34 Archive leaderboard report
Multi-Label Classification NUS-WIDE TResNet-L (resolution 448) MAP 65.2 #4 of 9 Archive leaderboard report
Multi-Label Classification OpenImages-v6 TResNet-L mAP 86.3 #4 of 4 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 TResNet-L (resolution 448, pretrain from MS-COCO) mAP 95.8 #8 of 17 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 TResNet-L (resolution 448, pretrain from ImageNet) mAP 94.6 #12 of 17 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