Browse State-of-the-Art › Weakly-Supervised Object Localization
Weakly-Supervised Object Localization
82 papers with code · 8 benchmarks · 3 datasets archive 2025-07-28
Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
8 leaderboard tables shown for this task, 8 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.
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
3 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: 140 · with a code link: 82 · where Syntology ran a sample: 16 (11 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (16 of 140 tagged: 11 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 140, 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.
-
14 Dec 2015 35 repositories listed Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified (of 17 harvested samples) · 3 pointer-only (licence)In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on…
-
22 Jun 2021 3 repositories listedTo evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.
-
1 Aug 2020 3 repositories listedAt the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features given a set of data.
-
13 Apr 2017 3 repositories listedWe propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos.
-
22 Sep 2023 2 repositories listedIn addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.
-
21 Jul 2022 2 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications.
-
25 Mar 2022 2 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)While class activation map (CAM) generated by image classification network has been widely used for weakly supervised object localization (WSOL) and semantic segmentation (WSSS), such classifiers usually focus on…
-
1 Dec 2021 2 repositories listedExisting FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator.
-
29 Sep 2021 2 repositories listedWe also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
-
27 Mar 2021 2 repositories listedTS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
-
19 Jul 2020 2 repositories listedCompared to classification networks, attention visualization for retrieval networks is hardly studied.
-
8 Jul 2020 2 repositories listedIn this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
-
21 Jan 2020 2 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.
-
19 Apr 2018 2 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)With such an adversarial learning, the two parallel-classifiers are forced to leverage complementary object regions for classification and can finally generate integral object localization together.
-
1 Jul 2017 2 repositories listedThis paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features.
-
31 Mar 2025 1 repository listedThey also face the well-known issue of asynchronous convergence between classification and localization tasks.
-
22 Jan 2025 1 repository listedWeakly supervised object localization (WSOL) using classification models trained with only image-class labels remains an important challenge in computer vision.
-
8 Jul 2024 1 repository listedOur TrCAM-V method allows training a localization network by sampling pseudo-pixels on the fly from these regions.
-
23 May 2024 1 repository listedA fundamental limitation to the development of 3D saliency methods is the lack of a benchmark to quantitatively assess these on 3D data.
-
29 Apr 2024 1 repository listedA WSOL model initially trained on some labeled source image data can be adapted using unlabeled target data in cases of significant domain shifts caused by variations in staining, scanners, and cancer type.
-
15 Apr 2024 1 repository listedThese bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations.
-
11 Mar 2024 1 repository listedThe reason for the high-performance of large kernel CNNs in downstream tasks has been attributed to the large effective receptive field (ERF) produced by large size kernels, but this view has not been fully tested.
-
16 Dec 2023 1 repository listedWhile foveation enables it to process different regions of the input with variable degrees of detail, saccades allow it to change the focus point of such foveated regions.
-
9 Oct 2023 1 repository listedSubsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.
-
17 Sep 2023 1 repository listedTo the best of our knowledge, we are the first to address this task.
-
19 Jul 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)During training, GenPromp converts image category labels to learnable prompt embeddings which are fed to a generative model to conditionally recover the input image with noise and learn representative embeddings.
-
17 Apr 2023 1 repository listedTo handle such data, we propose a novel paradigm of contrastive representation co-learning using both labeled and unlabeled data to generate a complete G-CAM (Generalized Class Activation Map) for object localization…
-
18 Mar 2023 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.
-
3 Jan 2023 1 repository listedPrevious weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when relying solely on image-level labels.
-
1 Jan 2023 1 repository listedVision transformers use [CLS] tokens to predict image classes.
-
9 Dec 2022 1 repository listed
-
31 Oct 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)
-
30 Sep 2022 1 repository listed
-
3 Aug 2022 1 repository listed
-
20 Jul 2022 1 repository listed
-
16 Jul 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
27 May 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)
-
14 Apr 2022 1 repository listed
-
7 Apr 2022 1 repository listed
-
27 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
3 Mar 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
29 Dec 2021 1 repository listed
-
1 Dec 2021 1 repository listed
-
26 Nov 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
12 Oct 2021 1 repository listed
-
15 Sep 2021 1 repository listed
-
13 Sep 2021 1 repository listed
-
2 Aug 2021 1 repository listed
-
28 Jul 2021 1 repository listed Syntology 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
19 Jun 2021 1 repository listed
-
15 Jun 2021 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
21 Apr 2021 1 repository listed
-
30 Mar 2021 1 repository listed
-
8 Mar 2021 1 repository listed
-
1 Jan 2021 1 repository listed
-
25 Sep 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
19 Jul 2020 1 repository listed
-
9 Jun 2020 1 repository listed
-
23 Apr 2020 1 repository listed
-
18 Mar 2020 1 repository listed
-
9 Mar 2020 1 repository listed
-
26 Feb 2020 1 repository listed
-
13 Feb 2020 1 repository listed
-
3 Dec 2019 1 repository listed
-
29 Nov 2019 1 repository listed
-
25 Nov 2019 1 repository listed
-
12 Oct 2019 1 repository listed
-
1 Oct 2019 1 repository listed
-
8 Sep 2019 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
25 Jul 2019 1 repository listed
-
11 Apr 2019 1 repository listed
-
7 Apr 2019 1 repository listed
-
16 Feb 2019 1 repository listed
-
4 Dec 2018 1 repository listed
-
24 Jul 2018 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
12 Oct 2017 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
6 Sep 2017 1 repository listed
-
14 Sep 2016 1 repository listed
-
Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization8 May 2025 0 repositories listed
-
Categorical Knowledge Fused Recognition: Fusing Hierarchical Knowledge with Image Classification through Aligning and Deep Metric Learning30 Jul 2024 0 repositories listed
-
Leveraging Activations for Superpixel Explanations7 Jun 2024 0 repositories listed
-
Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label15 Apr 2024 0 repositories listed
-
Towards Two-Stream Foveation-based Active Vision Learning24 Mar 2024 0 repositories listed
-
Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization15 Dec 2023 0 repositories listed
-
Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization4 Sep 2023 0 repositories listed
-
Rethinking the Localization in Weakly Supervised Object Localization11 Aug 2023 0 repositories listed
-
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization24 May 2023 0 repositories listed
-
Category-aware Allocation Transformer for Weakly Supervised Object Localization1 Jan 2023 0 repositories listed
-
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization9 Sep 2022 0 repositories listed
-
9 Sep 2022 0 repositories listed
-
Location-free Human Pose Estimation25 May 2022 0 repositories listed
-
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition22 Apr 2022 0 repositories listed
-
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization11 Apr 2022 0 repositories listed
-
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization1 Apr 2022 0 repositories listed
-
Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization18 Mar 2022 0 repositories listed
-
CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization3 Jan 2022 0 repositories listed
Syntology lines on 19 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