{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2007.08176","title":"CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","created":"2020-07-16","cited_by_count":441},{"id":"2110.06207","title":"Open-Set Recognition: a Good Closed-Set Classifier is All You Need?","created":"2021-10-12","cited_by_count":353},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2201.02609","title":"Generalized Category Discovery","created":"2022-01-07","cited_by_count":211},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2102.03526","title":"Open-World Semi-Supervised Learning","created":"2021-02-06","cited_by_count":165},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"2211.11727","title":"Parametric Classification for Generalized Category Discovery: A Baseline Study","created":"2022-11-21","cited_by_count":113},{"id":"2303.17393","title":"Dynamic Conceptional Contrastive Learning for Generalized Category Discovery","created":"2023-03-30","cited_by_count":92},{"id":"2212.05590","title":"PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery","created":"2022-12-11","cited_by_count":87},{"id":"2305.06144","title":"Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery","created":"2023-05-10","cited_by_count":72},{"id":"2311.17055","title":"No Representation Rules Them All in Category Discovery","created":"2023-11-28","cited_by_count":61},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58},{"id":"2403.13684","title":"SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning","created":"2024-03-20","cited_by_count":51},{"id":"2208.01898","title":"XCon: Learning with Experts for Fine-grained Category Discovery","created":"2022-08-03","cited_by_count":50},{"id":"2405.02363","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","created":"2024-05-03","cited_by_count":44},{"id":"2310.19776","title":"Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery","created":"2023-10-30","cited_by_count":39},{"id":"2404.09451","title":"Contrastive Mean-Shift Learning for Generalized Category Discovery","created":"2024-04-15","cited_by_count":39},{"id":"2310.11989","title":"Image Clustering with External Guidance","created":"2023-10-18","cited_by_count":36},{"id":"2108.00049","title":"Object-aware Contrastive Learning for Debiased Scene Representation","created":"2021-07-30","cited_by_count":35},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35},{"id":"2408.14371","title":"SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery","created":"2024-08-26","cited_by_count":34},{"id":"2403.05854","title":"LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content","created":"2024-03-09","cited_by_count":33},{"id":"2403.07369","title":"Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery","created":"2024-03-12","cited_by_count":31},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30},{"id":"2403.09974","title":"GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery","created":"2024-03-15","cited_by_count":27},{"id":"2304.06928","title":"CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery","created":"2023-04-14","cited_by_count":26},{"id":"2310.18297","title":"Image Clustering Conditioned on Text Criteria","created":"2023-10-27","cited_by_count":26},{"id":"2305.10420","title":"CLIP-GCD: Simple Language Guided Generalized Category Discovery","created":"2023-05-17","cited_by_count":25},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25},{"id":"2307.09158","title":"Class-relation Knowledge Distillation for Novel Class Discovery","created":"2023-07-18","cited_by_count":23},{"id":"2404.15655","title":"Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering","created":"2024-04-24","cited_by_count":21},{"id":"2303.13043","title":"Top-Down Visual Attention from Analysis by Synthesis","created":"2023-03-23","cited_by_count":19},{"id":"2304.01042","title":"DivClust: Controlling Diversity in Deep Clustering","created":"2023-04-03","cited_by_count":18},{"id":"2210.00314","title":"Learning Hierarchical Image Segmentation For Recognition and By Recognition","created":"2022-10-01","cited_by_count":16},{"id":"2306.13023","title":"AugDMC: Data Augmentation Guided Deep Multiple Clustering","created":"2023-06-22","cited_by_count":15},{"id":"2411.03978","title":"Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning","created":"2024-11-06","cited_by_count":12},{"id":"2302.14483","title":"RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data","created":"2023-02-28","cited_by_count":10},{"id":"2304.02364","title":"What's in a Name? Beyond Class Indices for Image Recognition","created":"2023-04-05","cited_by_count":9},{"id":"2409.11624","title":"Multimodal Generalized Category Discovery","created":"2024-09-18","cited_by_count":7},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7},{"id":"2212.06595","title":"OAMixer: Object-aware Mixing Layer for Vision Transformers","created":"2022-12-13","cited_by_count":4},{"id":"2310.19210","title":"Generalized Category Discovery with Clustering Assignment Consistency","created":"2023-10-30","cited_by_count":4},{"id":"2404.08995","title":"Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery","created":"2024-04-13","cited_by_count":4},{"id":"2510.14737","title":"Free-Grained Hierarchical Visual Recognition","created":"2025-10-16","cited_by_count":3}],"next_cursor":null}