{"total":125,"rows":[{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116,"area":null},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107,"area":null},{"id":"2111.09833","title":"TransMix: Attend to Mix for Vision Transformers","created":"2021-11-18","cited_by_count":79,"area":null},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78,"area":null},{"id":"2307.15254","title":"Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification","created":"2023-07-28","cited_by_count":60,"area":null},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2312.09627","title":"TF-CLIP: Learning Text-free CLIP for Video-based Person Re-Identification","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2202.04298","title":"Image Difference Captioning with Pre-training and Contrastive Learning","created":"2022-02-09","cited_by_count":39,"area":null},{"id":"2403.10254","title":"Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification","created":"2024-03-15","cited_by_count":35,"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":"2210.05958","title":"Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets","created":"2022-10-12","cited_by_count":29,"area":null},{"id":"2203.02751","title":"MetaFormer: A Unified Meta Framework for Fine-Grained Recognition","created":"2022-03-05","cited_by_count":28,"area":null},{"id":"2304.03119","title":"Zero-shot Generative Model Adaptation via Image-specific Prompt Learning","created":"2023-04-06","cited_by_count":27,"area":null},{"id":"2203.05922","title":"Visualizing and Understanding Patch Interactions in Vision Transformer","created":"2022-03-11","cited_by_count":26,"area":null},{"id":"2303.06442","title":"Fine-grained Visual Classification with High-temperature Refinement and Background Suppression","created":"2023-03-11","cited_by_count":22,"area":null},{"id":"2203.01536","title":"Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work","created":"2022-03-03","cited_by_count":21,"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":"2307.09756","title":"Generative Prompt Model for Weakly Supervised Object Localization","created":"2023-07-19","cited_by_count":20,"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":"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":"2203.03253","title":"Dynamic MLP for Fine-Grained Image Classification by Leveraging Geographical and Temporal Information","created":"2022-03-07","cited_by_count":15,"area":null},{"id":"2303.09117","title":"Cross-Modal Causal Intervention for Medical Report Generation","created":"2023-03-16","cited_by_count":15,"area":null},{"id":"2309.08912","title":"Delving into Multimodal Prompting for Fine-grained Visual Classification","created":"2023-09-16","cited_by_count":14,"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":"2401.04716","title":"Low-Resource Vision Challenges for Foundation Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2501.09333","title":"Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis","created":"2025-01-16","cited_by_count":12,"area":null},{"id":"2202.03822","title":"A Novel Plug-in Module for Fine-Grained Visual Classification","created":"2022-02-08","cited_by_count":11,"area":null},{"id":"2208.01838","title":"Re-Attention Transformer for Weakly Supervised Object Localization","created":"2022-08-03","cited_by_count":11,"area":null},{"id":"2309.14183","title":"Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition","created":"2023-09-25","cited_by_count":11,"area":null},{"id":"2203.01726","title":"Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2205.13282","title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","created":"2022-05-26","cited_by_count":10,"area":null},{"id":"2210.08473","title":"1st Place Solution in Google Universal Images Embedding","created":"2022-10-16","cited_by_count":10,"area":null},{"id":"2407.08027","title":"Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images","created":"2024-07-10","cited_by_count":9,"area":null},{"id":"2204.10095","title":"R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction","created":"2022-04-21","cited_by_count":8,"area":null},{"id":"2209.03846","title":"Transformer based Fingerprint Feature Extraction","created":"2022-09-08","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":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2403.04151","title":"Dual-path Frequency Discriminators for Few-shot Anomaly Detection","created":"2024-03-07","cited_by_count":7,"area":null},{"id":"2403.05297","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","created":"2024-03-08","cited_by_count":7,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","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":"2305.07180","title":"Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2208.01997","title":"Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization","created":"2022-08-03","cited_by_count":5,"area":null},{"id":"2212.07055","title":"Most Important Person-guided Dual-branch Cross-Patch Attention for Group Affect Recognition","created":"2022-12-14","cited_by_count":5,"area":null},{"id":"2303.14153","title":"Local Contrastive Learning for Medical Image Recognition","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2306.04893","title":"Coping with Change: Learning Invariant and Minimum Sufficient Representations for Fine-Grained Visual Categorization","created":"2023-06-08","cited_by_count":4,"area":null},{"id":"2405.13781","title":"Addressing the Elephant in the Room: Robust Animal Re-Identification with Unsupervised Part-Based Feature Alignment","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2407.12891","title":"Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformers","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2503.12385","title":"Car-1000: A New Large Scale Fine-Grained Visual Categorization Dataset","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2505.20866","title":"Respond to Change with Constancy: Instruction-tuning with LLM for Non-I.I.D. Network Traffic Classification","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2305.07102","title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","created":"2023-05-11","cited_by_count":3,"area":null},{"id":"2401.01858","title":"Synthetic dataset of ID and Travel Document","created":"2024-01-03","cited_by_count":3,"area":null},{"id":"2403.10298","title":"Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2306.02346","title":"Concept Drift and Long-Tailed Distribution in Fine-Grained Visual Categorization: Benchmark and Method","created":"2023-06-04","cited_by_count":2,"area":null},{"id":"2307.14825","title":"Simplified Concrete Dropout -- Improving the Generation of Attribution Masks for Fine-grained Classification","created":"2023-07-27","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":"2509.15688","title":"Saccadic Vision for Fine-Grained Visual Classification","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2512.19934","title":"Vehicle-centric Perception via Multimodal Structured Pre-training","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2203.12816","title":"ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2206.01153","title":"Multi-View Active Fine-Grained Recognition","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2207.01216","title":"Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022","created":"2022-07-04","cited_by_count":1,"area":null},{"id":"2208.08900","title":"Conviformers: Convolutionally guided Vision Transformer","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2208.12623","title":"From WSI-level to Patch-level: Structure Prior Guided Binuclear Cell Fine-grained Detection","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2210.02149","title":"Relational Proxies: Emergent Relationships as Fine-Grained Discriminators","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2210.04613","title":"Enhancing Fine-Grained 3D Object Recognition using Hybrid Multi-Modal Vision Transformer-CNN Models","created":"2022-10-03","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":"2301.02969","title":"Multi-scale multi-modal micro-expression recognition algorithm based on transformer","created":"2023-01-08","cited_by_count":1,"area":null},{"id":"2303.13404","title":"MSFA-Frequency-Aware Transformer for Hyperspectral Images Demosaicing","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.03351","title":"Leaf Cultivar Identification via Prototype-enhanced Learning","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2310.07028","title":"Facial Forgery-based Deepfake Detection using Fine-Grained Features","created":"2023-10-10","cited_by_count":1,"area":null},{"id":"2401.08860","title":"Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2401.14336","title":"Progressive Multi-task Anti-Noise Learning and Distilling Frameworks for Fine-grained Vehicle Recognition","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2401.17050","title":"ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2403.04066","title":"LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition","created":"2024-03-06","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":"2406.19814","title":"Extract More from Less: Efficient Fine-Grained Visual Recognition in Low-Data Regimes","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2408.13542","title":"Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2409.11051","title":"Down-Sampling Inter-Layer Adapter for Parameter and Computation Efficient Ultra-Fine-Grained Image Recognition","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2501.00243","title":"Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2505.23365","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2601.03729","title":"MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Species","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2106.10086","title":"It's FLAN time! Summing feature-wise latent representations for interpretability","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2112.04223","title":"Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition","created":"2021-12-08","cited_by_count":0,"area":null},{"id":"2207.11637","title":"Explored An Effective Methodology for Fine-Grained Snake Recognition","created":"2022-07-24","cited_by_count":0,"area":null},{"id":"2209.09857","title":"Fine-grained Classification of Solder Joints with {\\alpha}-skew Jensen-Shannon Divergence","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2209.10074","title":"PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification","created":"2022-09-21","cited_by_count":0,"area":null},{"id":"2302.10275","title":"Semantic Feature Integration network for Fine-grained Visual Classification","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2305.10432","title":"Model-Contrastive Federated Domain Adaptation","created":"2023-05-07","cited_by_count":0,"area":null},{"id":"2305.18680","title":"Improving Deep Representation Learning via Auxiliary Learnable Target Coding","created":"2023-05-30","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":"2310.08304","title":"CHIP: Contrastive Hierarchical Image Pretraining","created":"2023-10-12","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":"2312.14999","title":"Leveraging Habitat Information for Fine-grained Bird Identification","created":"2023-12-22","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":"2405.04093","title":"DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects","created":"2024-05-07","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":"2408.01998","title":"What Happens Without Background? Constructing Foreground-Only Data for Fine-Grained Tasks","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2408.07269","title":"Image-Based Leopard Seal Recognition: Approaches and Challenges in Current Automated Systems","created":"2024-08-14","cited_by_count":0,"area":null}],"next_cursor":"100"}