Self-produced Guidance for Weakly-supervised Object Localization
Not on the map. Why?
Abstract (arXiv)
Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We propose to generate Self-produced Guidance (SPG) masks which separate the foreground, the object of interest, from the background to provide the classification networks with spatial correlation information of pixels. A stagewise approach is proposed to incorporate high confident object regions to learn the SPG masks. The high confident regions within attention maps are utilized to progressively learn the SPG masks. The masks are then used as an auxiliary pixel-level supervision to facilitate the training of classification networks. Extensive experiments on ILSVRC demonstrate that SPG is effective in producing high-quality object localizations maps. Particularly, the proposed SPG achieves the Top-1 localization error rate of 43.83% on the ILSVRC validation set, which is a new state-of-the-art error rate.
Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jul 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 28; 2022: 20; 2023: 13; 2024: 6; 2025: 2; 2026: 3.
72 papers.
Sort:
By area:
- 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
- 2021UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modelingcited by 122
- 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
- 2021Large-Scale Unsupervised Object Discoverycited by 54
- 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
- 2021Shallow Feature Matters for Weakly Supervised Object Localizationcited by 34
- 2021Contrastive Syn-to-Real Generalizationcited by 32
- 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
- 2021Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localizationcited by 30
- 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
- 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localizationcited by 25
- 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localizationcited by 24
38 more
- 2021Background Activation Suppression for Weakly Supervised Object Localizationcited by 22
- 2022CREAM: Weakly Supervised Object Localization via Class RE-Activation Mappingcited by 21
- 2022Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibrationcited by 20
- 2023Generative Prompt Model for Weakly Supervised Object Localizationcited by 20
- 2021Just Noticeable Difference for Deep Machine Visioncited by 19
- 2021Normalization Matters in Weakly Supervised Object Localizationcited by 19
- 2022HINT: Hierarchical Neuron Concept Explainercited by 17
- 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentationcited by 17
- 2022Weakly Supervised Object Localization as Domain Adaptioncited by 16
- 2021Keep CALM and Improve Visual Feature Attributioncited by 15
- 2022ViTOL: Vision Transformer for Weakly Supervised Object Localizationcited by 13
- 2022Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 13
- 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
- 2022On Label Granularity and Object Localizationcited by 12
- 2022TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videoscited by 12
- 2022A Novel Plug-in Module for Fine-Grained Visual Classificationcited by 11
- 2022Re-Attention Transformer for Weakly Supervised Object Localizationcited by 11
- 2022Bagging Regional Classification Activation Maps for Weakly Supervised Object Localizationcited by 9
- 2022Negative Evidence Matters in Interpretable Histology Image Classificationcited by 8
- 2022Fine-Grained Visual Classification using Self Assessment Classifiercited by 8
- 2023DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localizationcited by 8
- 2021DAP: Detection-Aware Pre-training with Weak Supervisioncited by 7
- 2021Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosiscited by 7
- 2022Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentationcited by 7
- 2022Scaling Novel Object Detection with Weakly Supervised Detection Transformerscited by 7
- 2023CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videoscited by 7
- 2023Spatial-Aware Token for Weakly Supervised Object Localizationcited by 7
- 2021Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Surveycited by 6
- 2021Background-aware Classification Activation Map for Weakly Supervised Object Localizationcited by 6
- 2022Constrained Sampling for Class-Agnostic Weakly Supervised Object Localizationcited by 6
- 2021Weakly Supervised Thoracic Disease Localization via Disease Maskscited by 5
- 2021Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decompositioncited by 4
- 2021SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Costcited by 4
- 2022CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localizationcited by 4
- 2023Knowledge-guided Causal Intervention for Weakly-supervised Object Localizationcited by 4
- 2023Top-Down Framework for Weakly-supervised Grounded Image Captioningcited by 4
- 2021MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localizationcited by 3
- 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localizationcited by 3
50 most cited of 72 All 72 (JSON)
- 2026Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection5 Sep 2026
- 2026Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations12 Aug 2026
- 2026TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement26 Feb 2026
- 2025HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization30 Aug 2025
- 2025TeD-Loc: Text Distillation for Weakly Supervised Object Localization22 Jan 2025
- 2024Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos8 Jul 2024
- 2024ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding6 Jun 2024
- 2024Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet23 May 2024
- 2024Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label15 Apr 2024
- 2024CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective11 Mar 2024
- 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning24 Feb 2024
- 2023Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization15 Dec 2023
38 more
- 2023DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization9 Oct 2023
- 2023Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation22 Sep 2023
- 2023FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object Localization17 Sep 2023
- 2023Unsupervised Object Localization with Representer Point Selection8 Sep 2023
- 2023Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization4 Sep 2023
- 2023Generative Prompt Model for Weakly Supervised Object Localization19 Jul 2023
- 2023Top-Down Framework for Weakly-supervised Grounded Image Captioning13 Jun 2023
- 2023Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization24 May 2023
- 2023Open-World Weakly-Supervised Object Localization17 Apr 2023
- 2023Spatial-Aware Token for Weakly Supervised Object Localization18 Mar 2023
- 2023CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos16 Mar 2023
- 2023Knowledge-guided Causal Intervention for Weakly-supervised Object Localization3 Jan 2023
- 2022Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization9 Sep 2022
- 2022Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization9 Sep 2022
- 2022TCAM: Temporal Class Activation Maps for Object Localization in Weakly-Labeled Unconstrained Videos30 Aug 2022
- 2022Re-Attention Transformer for Weakly Supervised Object Localization3 Aug 2022
- 2022Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration21 Jul 2022
- 2022On Label Granularity and Object Localization20 Jul 2022
- 2022Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization16 Jul 2022
- 2022Scaling Novel Object Detection with Weakly Supervised Detection Transformers11 Jul 2022
- 2022CREAM: Weakly Supervised Object Localization via Class RE-Activation Mapping27 May 2022
- 2022Fine-Grained Visual Classification using Self Assessment Classifier21 May 2022
- 2022ViTOL: Vision Transformer for Weakly Supervised Object Localization14 Apr 2022
- 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization11 Apr 2022
- 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization1 Apr 2022
- 2022HINT: Hierarchical Neuron Concept Explainer27 Mar 2022
- 2022Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation25 Mar 2022
- 2022Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization18 Mar 2022
- 2022Weakly Supervised Object Localization as Domain Adaption3 Mar 2022
- 2022A Novel Plug-in Module for Fine-Grained Visual Classification8 Feb 2022
- 2022Negative Evidence Matters in Interpretable Histology Image Classification7 Jan 2022
- 2022CaFT: Clustering and Filter on Tokens of Transformer for Weakly Supervised Object Localization3 Jan 2022
- 2021Background-aware Classification Activation Map for Weakly Supervised Object Localization29 Dec 2021
- 2021Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception27 Dec 2021
- 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization10 Dec 2021
- 2021Background Activation Suppression for Weakly Supervised Object Localization1 Dec 2021
- 2021Learning a Weight Map for Weakly-Supervised Localization28 Nov 2021
- 2021UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling23 Nov 2021
50 newest of 72 All 72 (JSON)
- 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
- 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
- 2021Large-Scale Unsupervised Object Discoverycited by 54
- 2021Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localizationcited by 46
- 2021Shallow Feature Matters for Weakly Supervised Object Localizationcited by 34
- 2021Contrastive Syn-to-Real Generalizationcited by 32
- 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
- 2021Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localizationcited by 30
- 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
- 2022Bridging the Gap between Classification and Localization for Weakly Supervised Object Localizationcited by 25
- 2021LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localizationcited by 24
- 2021Background Activation Suppression for Weakly Supervised Object Localizationcited by 22
12 most cited of 71 All 71 (JSON)
- 2026Spatial Attention Supervision for Defect Localization: Exploiting Ground-Truth Masks as Training Signal in Diffusion-Augmented Defect Detection5 Sep 2026
- 2026Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN, Transformer, and Foundation-Model-Era Visual Explanations12 Aug 2026
- 2026TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement26 Feb 2026
- 2025HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization30 Aug 2025
- 2025TeD-Loc: Text Distillation for Weakly Supervised Object Localization22 Jan 2025
- 2024Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos8 Jul 2024
- 2024ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding6 Jun 2024
- 2024Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet23 May 2024
- 2024Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label15 Apr 2024
- 2024CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective11 Mar 2024
- 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning24 Feb 2024
- 2023Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization15 Dec 2023
12 newest of 71 All 71 (JSON)