Browse State-of-the-Art › Multi-label Image Recognition with Partial Labels
Multi-label Image Recognition with Partial Labels
8 papers with code · 3 benchmarks · 2 datasets archive 2025-07-28
Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each multi-label image, aims to train MLR models with partial labels to reduce the annotation cost. Since existing MLR datasets have complete labels, current works propose to randomly drop a certain proportion of positive and negative labels to create partially annotated datasets, and report the results on the known labels proportion of 10% to 90%.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| MS-COCO-2014 (6 rows) | DualCoOp+TaI-DPT | Texts as Images in Prompt Tuning for Multi-Label Image Recognition | code | — | Compare |
| PASCAL VOC 2007 (6 rows) | DualCoOp+TaI-DPT | Texts as Images in Prompt Tuning for Multi-Label Image Recognition | code | — | Compare |
| Visual Genome (4 rows) | DSRB | Dual-Perspective Semantic-Aware Representation Blending for... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 11 · with a code link: 8 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 11 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 11 of 11, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
20 Aug 2019 2 repositories listedRecognizing multiple labels of images is a practical and challenging task, and significant progress has been made by searching semantic-aware regions and modeling label dependency.
-
23 Nov 2022 1 repository listedNonetheless, visual data (e. g., images) is by default prerequisite for learning prompts in existing methods.
-
20 Jun 2022 1 repository listedSolving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications.
-
26 May 2022 1 repository listedSpecifically, an instance-perspective representation blending (IPRB) module is designed to blend the representations of the known labels in an image with the representations of the corresponding unknown labels in…
-
23 May 2022 1 repository listedMulti-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR.
-
4 Mar 2022 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)However, these algorithms depend on sufficient multi-label annotations to train the models, leading to poor performance especially with low known label proportion.
-
21 Dec 2021 1 repository listedTo reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i. e., merely some labels are known while other labels…
-
3 Mar 2021 1 repository listedThe task of multi-label image recognition is to predict a set of object labels that present in an image.
-
Saliency Regularization for Self-Training with Partial Annotations1 Jan 2023 0 repositories listedPartially annotated images are easy to obtain in multi-label classification.
-
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition20 Sep 2020 0 repositories listedRecognizing multiple labels of an image is a practical yet challenging task, and remarkable progress has been achieved by searching for semantic regions and exploiting label dependencies.
-
Learning a Deep ConvNet for Multi-label Classification with Partial Labels26 Feb 2019 0 repositories listedDeep ConvNets have shown great performance for single-label image classification (e.g. ImageNet), but it is necessary to move beyond the single-label classification task because pictures of everyday life are inherently…
Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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