Papers › Query2Label: A Simple Transformer Way to Multi-Label Classification

Query2Label: A Simple Transformer Way to Multi-Label Classification

22 Jul 2021arXiv:2107.10834archive 2025-07-28

Shilong Liu, Lei Zhang, Xiao Yang, Hang Su, Jun Zhu

This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label. The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image. The built-in cross-attention module in the Transformer decoder offers an effective way to use label embeddings as queries to probe and pool class-related features from a feature map computed by a vision backbone for subsequent binary classifications. Compared with prior works, the new framework is simple, using standard Transformers and vision backbones, and effective, consistently outperforming all previous works on five multi-label classification data sets, including MS-COCO, PASCAL VOC, NUS-WIDE, and Visual Genome. Particularly, we establish 91.3% mAP on MS-COCO. We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies. The code will be available soon at https://github.com/SlongLiu/query2labels.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2107.10834")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · fixture could not drive it.

By repository: official repository: 2 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.

SlongLiu/query2labels officialmentioned in papermentioned on GitHubpytorch report
averyfallson/rmffn mentioned on GitHubpytorch report
curt-tigges/query2label mentioned on GitHubpytorch 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

2 samples harvested; 2 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

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

Licence: 0 of the 2 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 SlongLiu/query2labels. “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.

kill_process SlongLiu/query2labels/q2l_infer.py official repository ran · honoured contract MIT (permissive) · 6840401a1f3d4796 · report
train SlongLiu/query2labels/main_mlc.py official repository ran · fixture could not drive it MIT (permissive) · 5aa56052c6f9f021 · report

Tasks

ClassificationDecoderMUlTI-LABEL-ClASSIFICATIONMulti-Label Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Label Classification MS-COCO Q2L-CvT(ImageNet-21K pretraining, resolution 384) mAP 91.3 #5 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO Q2L-SwinL(ImageNet-21K pretraining, resolution 384) mAP 90.5 #8 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO Q2L-TResL(ImageNet-21K pretraining, resolution 640) mAP 90.3 #9 of 34 Archive leaderboard report
Multi-Label Classification MS-COCO Q2L-R101(resolution 448) mAP 84.9 #25 of 34 Archive leaderboard report
Multi-Label Classification NUS-WIDE Q2L-CvT(resolution 384, ImageNet-21K pretrained) MAP 70.1 #1 of 9 Archive leaderboard report
Multi-Label Classification NUS-WIDE Q2L-TResL(resoluition 448) MAP 66.3 #3 of 9 Archive leaderboard report
Multi-Label Classification NUS-WIDE Q2L-R101(resolution 448) MAP 65.0 #5 of 9 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 Q2L-CvT(ImageNet-21K pretrained, resolution 384) mAP 97.3 #1 of 17 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 Q2L-TResL(ImageNet-21K pretrained, resolution 448) mAP 96.9 #2 of 17 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2007 Q2L-TResL(resolution 448) mAP 96.1 #6 of 17 Archive leaderboard report
Multi-Label Classification PASCAL VOC 2012 Q2L-TResL(448 resolution) mAP 96.2 #1 of 3 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.

Methods

Absolute Position EncodingsAdamAttentionBPEConcatenated Skip ConnectionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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