Browse State-of-the-Art › Weakly Supervised Object Detection

Weakly Supervised Object Detection

58 papers with code · 17 benchmarks · 14 datasets archive 2025-07-28

Computer Vision

Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.

( Image credit: Soft Proposal Networks for Weakly Supervised Object Localization )

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

17 leaderboard tables shown for this task, 17 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. 10 shown of 17 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
PASCAL VOC 2007 (41 rows) WeakSAM-MIST-DINO (with SAM) WeakSAM: Segment Anything Meets Weakly-supervised Instance-level... code — Compare
PASCAL VOC 2012 test (32 rows) WeakSAM-MIST-DINO (with SAM) WeakSAM: Segment Anything Meets Weakly-supervised Instance-level... code — Compare
Watercolor2k (12 rows) TADP Text-image Alignment for Diffusion-based Perception code — Compare
Comic2k (8 rows) DASS-Detector (YOLOX Tiny) Domain-Adaptive Self-Supervised Pre-Training for Face & Body... code — Compare
Clipart1k (7 rows) H2FA R-CNN (clipart_all) H2FA R-CNN: Holistic and Hierarchical Feature Alignment for... code — Compare
MS-COCO-2014 (7 rows) WeakSAM-MIST-DINO (with SAM) WeakSAM: Segment Anything Meets Weakly-supervised Instance-level... code — Compare
Charades (6 rows) Spatial Prior Activity Driven Weakly Supervised Object Detection — — Compare
COCO (Common Objects in Context) (5 rows) MSLPD Few-Example Object Detection with Model Communication code — Compare
ImageNet (4 rows) PCL-OB-G-Ens + FRCNN PCL: Proposal Cluster Learning for Weakly Supervised Object Detection code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified Compare
COCO test-dev (4 rows) wetectron(single-model, VGG16) Instance-aware, Context-focused, and Memory-efficient Weakly... code Syntology community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified Compare
HICO-DET (4 rows) Spatial Prior Activity Driven Weakly Supervised Object Detection — — Compare
PeopleArt (2 rows) Polyhedral MI-max Multiple instance learning on deep features for weakly supervised... code — Compare
Cityscapes-to-Foggy Cityscapes (2 rows) MEAA Domain-Adaptive Object Detection via Uncertainty-Aware... code — Compare
IconArt (2 rows) MI_Net [wang_revisiting_2018] Multiple instance learning on deep features for weakly supervised... code — Compare
CASPAPaintings (1 row) MI-max Multiple instance learning on deep features for weakly supervised... code — Compare
MS-COCO-2017 (1 row) OD-WSCL Object Discovery via Contrastive Learning for Weakly Supervised... code — Compare
MSCOCO (1 row) CASD(ResNet50) Comprehensive Attention Self-Distillation for Weakly-Supervised... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified 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

14 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: 142 · with a code link: 58 · where Syntology ran a sample: 15 (13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (15 of 142 tagged: 13 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 142, 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. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 15 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