Weakly-Supervised Object Localization

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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

Most implemented papers archive 2025-07-28

30 shown of 82 papers with code (140 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Learning Deep Features for Discriminative Localization
  14 Dec 2015 35 repositories listed Syntology ran 2 of 17 samples · 15 unverified · 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…
• LayerCAM: Exploring Hierarchical Class Activation Maps for Localization
  22 Jun 2021 3 repositories listed
  To evaluate the quality of the class activation maps produced by LayerCAM, we apply them to weakly-supervised object localization and semantic segmentation.
• Eigen-CAM: Class Activation Map using Principal Components
  1 Aug 2020 3 repositories listed
  At the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features given a set of data.
• Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
  13 Apr 2017 3 repositories listed
  We propose `Hide-and-Seek', a weakly-supervised framework that aims to improve object localization in images and action localization in videos.
• Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation
  22 Sep 2023 2 repositories listed
  In addition, our method also achieves state-of-the-art weakly supervised semantic segmentation performance on the PASCAL VOC 2012 and MS COCO 2014 datasets.
• Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
  21 Jul 2022 2 repositories listed Syntology ran 7 of 10 samples · 3 unverified
  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.
• Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation
  25 Mar 2022 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  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…
• Background Activation Suppression for Weakly Supervised Object Localization
  1 Dec 2021 2 repositories listed
  Existing FPM-based methods use cross-entropy (CE) to evaluate the foreground prediction map and to guide the learning of generator.
• Localizing Objects with Self-Supervised Transformers and no Labels
  29 Sep 2021 2 repositories listed
  We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points.
• TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization
  27 Mar 2021 2 repositories listed
  TS-CAM finally couples the patch tokens with the semantic-agnostic attention map to achieve semantic-aware localization.
• A Generic Visualization Approach for Convolutional Neural Networks
  19 Jul 2020 2 repositories listed
  Compared to classification networks, attention visualization for retrieval networks is hardly studied.
• Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets
  8 Jul 2020 2 repositories listed
  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.
• Evaluating Weakly Supervised Object Localization Methods Right
  21 Jan 2020 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 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.
• Adversarial Complementary Learning for Weakly Supervised Object Localization
  19 Apr 2018 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 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.
• WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
  1 Jul 2017 2 repositories listed
  This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features.
• PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization
  31 Mar 2025 1 repository listed
  They also face the well-known issue of asynchronous convergence between classification and localization tasks.
• TeD-Loc: Text Distillation for Weakly Supervised Object Localization
  22 Jan 2025 1 repository listed
  Weakly supervised object localization (WSOL) using classification models trained with only image-class labels remains an important challenge in computer vision.
• Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos
  8 Jul 2024 1 repository listed
  Our TrCAM-V method allows training a localization network by sampling pseudo-pixels on the fly from these regions.
• SE3D: A Framework For Saliency Method Evaluation In 3D Imaging
  23 May 2024 1 repository listed
  A fundamental limitation to the development of 3D saliency methods is the lack of a benchmark to quantitatively assess these on 3D data.
• Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology
  29 Apr 2024 1 repository listed
  A 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.
• A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
  15 Apr 2024 1 repository listed
  These bboxes are also employed to estimate the threshold from LOC maps, circumventing the need for test-set bbox annotations.
• CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective
  11 Mar 2024 1 repository listed
  The 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.
• Exploring Foveation and Saccade for Improved Weakly-Supervised Localization
  16 Dec 2023 1 repository listed
  While 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.
• DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization
  9 Oct 2023 1 repository listed
  Subsequently, these proposals are used as pseudo-labels to train our new transformer-based WSOL model designed to perform classification and localization tasks.
• FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization
  17 Sep 2023 1 repository listed
  To the best of our knowledge, we are the first to address this task.
• Generative Prompt Model for Weakly Supervised Object Localization
  19 Jul 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  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.
• Open-World Weakly-Supervised Object Localization
  17 Apr 2023 1 repository listed
  To 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,…
• Spatial-Aware Token for Weakly Supervised Object Localization
  18 Mar 2023 1 repository listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  Specifically, a spatial token is first introduced in the input space to aggregate representations for localization task.
• Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
  3 Jan 2023 1 repository listed
  Previous 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.
• Adversarial Normalization: I Can Visualize Everything (ICE)
  1 Jan 2023 1 repository listed
  Vision transformers use [CLS] tokens to predict image classes.

Syntology lines on 7 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. Read from the graph 2026-09-24.