{"total":75,"rows":[{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132,"area":null},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2203.15636","title":"Diffusion Models for Counterfactual Explanations","created":"2022-03-29","cited_by_count":79,"area":"diffusion"},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47,"area":"diffusion"},{"id":"2303.01494","title":"Image as Set of Points","created":"2023-03-02","cited_by_count":43,"area":null},{"id":"2404.16771","title":"ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving","created":"2024-04-25","cited_by_count":43,"area":null},{"id":"2201.13291","title":"Metrics for saliency map evaluation of deep learning explanation methods","created":"2022-01-31","cited_by_count":40,"area":null},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38,"area":null},{"id":"2107.08192","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","created":"2021-07-17","cited_by_count":34,"area":null},{"id":"2309.07944","title":"Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach","created":"2023-09-14","cited_by_count":28,"area":null},{"id":"2212.05853","title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","created":"2022-12-12","cited_by_count":25,"area":null},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25,"area":null},{"id":"2209.02109","title":"SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization","created":"2022-09-05","cited_by_count":21,"area":null},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21,"area":null},{"id":"2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","created":"2021-12-02","cited_by_count":19,"area":null},{"id":"2208.14607","title":"SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization","created":"2022-08-31","cited_by_count":19,"area":null},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17,"area":null},{"id":"2309.00399","title":"Fine-grained Recognition with Learnable Semantic Data Augmentation","created":"2023-09-01","cited_by_count":17,"area":null},{"id":"2107.04474","title":"Interpretable Compositional Convolutional Neural Networks","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2110.01240","title":"A free lunch from ViT:Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition","created":"2021-10-04","cited_by_count":16,"area":null},{"id":"2308.05396","title":"Learning Gabor Texture Features for Fine-Grained Recognition","created":"2023-08-10","cited_by_count":16,"area":null},{"id":"2208.02611","title":"Surgical Skill Assessment via Video Semantic Aggregation","created":"2022-08-04","cited_by_count":13,"area":null},{"id":"2507.06928","title":"Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2101.03919","title":"Comprehensible Convolutional Neural Networks via Guided Concept Learning","created":"2021-01-11","cited_by_count":11,"area":null},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11,"area":null},{"id":"2307.14433","title":"ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography","created":"2023-07-26","cited_by_count":11,"area":null},{"id":"2503.10247","title":"Interpretable Image Classification via Non-parametric Part Prototype Learning","created":"2025-03-13","cited_by_count":11,"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":"2407.04538","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2205.10529","title":"Fine-Grained Visual Classification using Self Assessment Classifier","created":"2022-05-21","cited_by_count":8,"area":null},{"id":"2111.03651","title":"The Curious Layperson: Fine-Grained Image Recognition without Expert Labels","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2212.12532","title":"Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers","created":"2022-12-23","cited_by_count":7,"area":null},{"id":"2212.13685","title":"Part-guided Relational Transformers for Fine-grained Visual Recognition","created":"2022-12-28","cited_by_count":7,"area":null},{"id":"2112.02747","title":"Making a Bird AI Expert Work for You and Me","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2203.13868","title":"Self-supervised Semantic Segmentation Grounded in Visual Concepts","created":"2022-03-25","cited_by_count":6,"area":null},{"id":"2310.16316","title":"Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2308.14418","title":"Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2503.16782","title":"Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2211.10630","title":"Explainable fetal ultrasound quality assessment with progressive concept bottleneck models","created":"2022-11-19","cited_by_count":3,"area":null},{"id":"2302.09561","title":"TAX: Tendency-and-Assignment Explainer for Semantic Segmentation with Multi-Annotators","created":"2023-02-19","cited_by_count":3,"area":null},{"id":"2103.03429","title":"Human-Understandable Decision Making for Visual Recognition","created":"2021-03-05","cited_by_count":2,"area":null},{"id":"2106.02566","title":"BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of Attention","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2106.11054","title":"Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2212.13693","title":"Parsing Objects at a Finer Granularity: A Survey","created":"2022-12-28","cited_by_count":2,"area":null},{"id":"2302.10266","title":"Kernel function impact on convolutional neural networks","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2308.02161","title":"M2Former: Multi-Scale Patch Selection for Fine-Grained Visual Recognition","created":"2023-08-04","cited_by_count":2,"area":null},{"id":"2408.08108","title":"Unsupervised Part Discovery via Dual Representation Alignment","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2503.06084","title":"Exploring Interpretability for Visual Prompt Tuning with Cross-layer Concepts","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2106.10920","title":"Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification","created":"2021-06-21","cited_by_count":1,"area":null},{"id":"2106.13164","title":"Towards Fully Interpretable Deep Neural Networks: Are We There Yet?","created":"2021-06-24","cited_by_count":1,"area":null},{"id":"2205.06546","title":"Comparison of attention models and post-hoc explanation methods for embryo stage identification: a case study","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2311.03547","title":"InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates","created":"2023-11-06","cited_by_count":1,"area":null},{"id":"2405.00468","title":"Feature-Aware Noise Contrastive Learning for Unsupervised Red Panda Re-Identification","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2406.08457","title":"ConceptHash: Interpretable Fine-Grained Hashing via Concept Discovery","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2507.09881","title":"Counterfactual Visual Explanation via Causally-Guided Adversarial Steering","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2507.11985","title":"Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2103.11888","title":"Weakly Supervised Recovery of Semantic Attributes","created":"2021-03-22","cited_by_count":0,"area":null},{"id":"2303.09269","title":"ELFIS: Expert Learning for Fine-grained Image Recognition Using Subsets","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2306.01929","title":"Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2307.16565","title":"Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation","created":"2023-07-31","cited_by_count":0,"area":null},{"id":"2310.09600","title":"Hawkeye: A PyTorch-based Library for Fine-Grained Image Recognition with Deep Learning","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2310.15999","title":"Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2407.04243","title":"Exploration of Class Center for Fine-Grained Visual Classification","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2409.06589","title":"Seg-HGNN: Unsupervised and Light-Weight Image Segmentation with Hyperbolic Graph Neural Networks","created":"2024-09-10","cited_by_count":0,"area":null},{"id":"2504.09215","title":"Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognition","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2603.14240","title":"FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domains","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2605.06095","title":"Metonymy in vision models undermines attention-based interpretability","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.22665","title":"Hyperbolic Hierarchical Clustering for Visual Representation Learning","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.36560","title":"FM-ReID: Selective Competitive Token Routing for Object Re-Identification","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}