{"total":98,"rows":[{"id":"2105.08965","title":"Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation","created":"2021-05-19","cited_by_count":127,"area":null},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123,"area":null},{"id":"2104.07918","title":"Weakly Supervised Object Localization and Detection: A Survey","created":"2021-04-16","cited_by_count":84,"area":null},{"id":"2103.13027","title":"AutoMix: Unveiling the Power of Mixup for Stronger Classifiers","created":"2021-03-24","cited_by_count":69,"area":null},{"id":"2203.03860","title":"Weakly Supervised Semantic Segmentation using Out-of-Distribution Data","created":"2022-03-08","cited_by_count":58,"area":null},{"id":"2110.03095","title":"Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54,"area":null},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"area":null},{"id":"2204.10437","title":"DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis","created":"2022-04-21","cited_by_count":48,"area":null},{"id":"2104.13243","title":"Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation","created":"2021-04-27","cited_by_count":37,"area":null},{"id":"2108.00049","title":"Object-aware Contrastive Learning for Debiased Scene Representation","created":"2021-07-30","cited_by_count":35,"area":null},{"id":"2109.07069","title":"F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2301.07002","title":"Opti-CAM: Optimizing saliency maps for interpretability","created":"2023-01-17","cited_by_count":25,"area":null},{"id":"2112.00580","title":"Background Activation Suppression for Weakly Supervised Object Localization","created":"2021-12-01","cited_by_count":22,"area":null},{"id":"2308.03005","title":"MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation","created":"2023-08-06","cited_by_count":22,"area":null},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2209.04851","title":"OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning","created":"2022-09-11","cited_by_count":21,"area":null},{"id":"2207.10447","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","created":"2022-07-21","cited_by_count":20,"area":null},{"id":"2107.13221","title":"Normalization Matters in Weakly Supervised Object Localization","created":"2021-07-28","cited_by_count":19,"area":null},{"id":"2309.12943","title":"Background Activation Suppression for Weakly Supervised Object Localization and Semantic Segmentation","created":"2023-09-22","cited_by_count":17,"area":null},{"id":"2309.06891","title":"Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?","created":"2023-09-13","cited_by_count":16,"area":null},{"id":"2106.07861","title":"Keep CALM and Improve Visual Feature Attribution","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2209.09209","title":"Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":13,"area":null},{"id":"2204.04890","title":"Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization","created":"2022-04-11","cited_by_count":12,"area":null},{"id":"2207.10225","title":"On Label Granularity and Object Localization","created":"2022-07-20","cited_by_count":12,"area":null},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2304.01804","title":"Bridging the Gap between Model Explanations in Partially Annotated Multi-label Classification","created":"2023-04-04","cited_by_count":11,"area":null},{"id":"2402.00281","title":"Guided Interpretable Facial Expression Recognition via Spatial Action Unit Cues","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2207.05054","title":"Demystifying Unsupervised Semantic Correspondence Estimation","created":"2022-07-11","cited_by_count":10,"area":null},{"id":"2106.15788","title":"Exploring Localization for Self-supervised Fine-grained Contrastive Learning","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2207.07818","title":"Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization","created":"2022-07-16","cited_by_count":9,"area":null},{"id":"2304.04875","title":"Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild","created":"2023-04-10","cited_by_count":9,"area":null},{"id":"2404.19113","title":"Source-Free Domain Adaptation of Weakly-Supervised Object Localization Models for Histology","created":"2024-04-29","cited_by_count":9,"area":null},{"id":"2201.02445","title":"Negative Evidence Matters in Interpretable Histology Image Classification","created":"2022-01-07","cited_by_count":8,"area":null},{"id":"2204.03643","title":"Total Variation Optimization Layers for Computer Vision","created":"2022-04-07","cited_by_count":8,"area":null},{"id":"2310.06196","title":"DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object Localization","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2103.16651","title":"DAP: Detection-Aware Pre-training with Weak Supervision","created":"2021-03-30","cited_by_count":7,"area":null},{"id":"2106.07049","title":"Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis","created":"2021-06-13","cited_by_count":7,"area":null},{"id":"2112.11895","title":"Few-shot Font Generation with Weakly Supervised Localized Representations","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2203.13505","title":"Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation","created":"2022-03-25","cited_by_count":7,"area":null},{"id":"2208.02337","title":"Estimating Visual Information From Audio Through Manifold Learning","created":"2022-08-03","cited_by_count":7,"area":null},{"id":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2303.10438","title":"Spatial-Aware Token for Weakly Supervised Object Localization","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2112.14379","title":"Background-aware Classification Activation Map for Weakly Supervised Object Localization","created":"2021-12-29","cited_by_count":6,"area":null},{"id":"2209.09195","title":"Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization","created":"2022-09-09","cited_by_count":6,"area":null},{"id":"2412.03215","title":"Beyond [cls]: Exploring the true potential of Masked Image Modeling representations","created":"2024-12-04","cited_by_count":6,"area":null},{"id":"2106.09011","title":"Evolving Image Compositions for Feature Representation Learning","created":"2021-06-16","cited_by_count":5,"area":null},{"id":"2404.10034","title":"A Realistic Protocol for Evaluation of Weakly Supervised Object Localization","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2407.19308","title":"Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector","created":"2024-07-27","cited_by_count":5,"area":null},{"id":"2301.01060","title":"Knowledge-guided Causal Intervention for Weakly-supervised Object Localization","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2303.17595","title":"Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2104.14375","title":"MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2108.03704","title":"OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning","created":"2021-08-08","cited_by_count":3,"area":null},{"id":"2110.00881","title":"Weakly Supervised Attention-based Models Using Activation Maps for Citrus Mite and Insect Pest Classification","created":"2021-10-02","cited_by_count":3,"area":null},{"id":"2305.15354","title":"Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2309.03874","title":"Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2309.04172","title":"Unsupervised Object Localization with Representer Point Selection","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2403.15977","title":"Towards Two-Stream Foveation-based Active Vision Learning","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2108.01785","title":"Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection","created":"2021-08-03","cited_by_count":2,"area":null},{"id":"2110.05182","title":"TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2205.01233","title":"One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model","created":"2022-05-02","cited_by_count":2,"area":null},{"id":"2304.08271","title":"Open-World Weakly-Supervised Object Localization","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2403.06676","title":"CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2407.06018","title":"Leveraging Transformers for Weakly Supervised Object Localization in Unconstrained Videos","created":"2024-07-08","cited_by_count":2,"area":null},{"id":"2501.12632","title":"TeD-Loc: Text Distillation for Weakly Supervised Object Localization","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.24135","title":"PixelCAM: Pixel Class Activation Mapping for Histology Image Classification and ROI Localization","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2505.06003","title":"From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2104.07954","title":"Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2111.14131","title":"Learning a Weight Map for Weakly-Supervised Localization","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2209.10471","title":"Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2211.15672","title":"ExpNet: A unified network for Expert-Level Classification","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2309.03509","title":"BroadCAM: Outcome-agnostic Class Activation Mapping for Small-scale Weakly Supervised Applications","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2401.10050","title":"ContextMix: A context-aware data augmentation method for industrial visual inspection systems","created":"2024-01-18","cited_by_count":1,"area":null},{"id":"2405.14563","title":"Concept Visualization: Explaining the CLIP Multi-modal Embedding Using WordNet","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2405.14584","title":"SE3D: A Framework For Saliency Method Evaluation In 3D Imaging","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2406.04493","title":"ReceiptSense: Beyond Traditional OCR -- A Dataset for Receipt Understanding","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2505.04905","title":"Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2104.04952","title":"Fine-Grained Attention for Weakly Supervised Object Localization","created":"2021-04-11","cited_by_count":0,"area":null},{"id":"2106.00180","title":"Dual Normalization Multitasking for Audio-Visual Sounding Object Localization","created":"2021-06-01","cited_by_count":0,"area":null},{"id":"2111.08401","title":"Weakly-supervised fire segmentation by visualizing intermediate CNN layers","created":"2021-11-16","cited_by_count":0,"area":null},{"id":"2112.15344","title":"P2P-Loc: Point to Point Tiny Person Localization","created":"2021-12-31","cited_by_count":0,"area":null},{"id":"2210.08645","title":"An efficient deep neural network to find small objects in large 3D images","created":"2022-10-16","cited_by_count":0,"area":null},{"id":"2403.05703","title":"Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2404.00918","title":"Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2406.04933","title":"Leveraging Activations for Superpixel Explanations","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2507.02308","title":"LMPNet for Weakly-supervised Keypoint Discovery","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2510.25134","title":"Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.05590","title":"Beyond Softmax: Dual-Branch Sigmoid Architecture for Accurate Class Activation Maps","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2602.23120","title":"TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.02946","title":"Learning from Synthetic Data via Provenance-Based Input Gradient Guidance","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2606.09855","title":"MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.14555","title":"Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.29581","title":"Explaining AI-Image Detection: What the Heatmap Actually Shows","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.19407","title":"HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2610.05891","title":"Spatial Supervision Without Attribution Optimization: Improving Post-Hoc Class Activation Maps via Box-Guided Evidence Routing","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}