{"list":"other","total":91,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1603.09320","title":"Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs","created":"2016-03-30","cited_by_count":861},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"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":"1911.04623","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","created":"2019-11-12","cited_by_count":195},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2003.04390","title":"Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning","created":"2020-03-09","cited_by_count":179},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"1511.08060","title":"An open access repository of images on plant health to enable the development of mobile disease diagnostics","created":"2015-11-25","cited_by_count":135},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"2203.07190","title":"CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment","created":"2022-03-14","cited_by_count":113},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"2304.01195","title":"Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement","created":"2023-04-03","cited_by_count":84},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75},{"id":"2105.07029","title":"Learning a Universal Template for Few-shot Dataset Generalization","created":"2021-05-14","cited_by_count":61},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56},{"id":"2402.04087","title":"A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation","created":"2024-02-06","cited_by_count":53},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52},{"id":"2306.01667","title":"Towards In-context Scene Understanding","created":"2023-06-02","cited_by_count":47},{"id":"2301.12246","title":"A Closer Look at Few-shot Classification Again","created":"2023-01-28","cited_by_count":46},{"id":"2103.15718","title":"von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning","created":"2021-03-29","cited_by_count":42},{"id":"2306.07196","title":"Retrieval-Enhanced Contrastive Vision-Text Models","created":"2023-06-12","cited_by_count":36},{"id":"1912.02738","title":"MetaFun: Meta-Learning with Iterative Functional Updates","created":"2019-12-05","cited_by_count":34},{"id":"2210.03794","title":"SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models","created":"2022-10-07","cited_by_count":34},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33},{"id":"2305.09253","title":"Online Continual Learning Without the Storage Constraint","created":"2023-05-16","cited_by_count":29},{"id":"2407.10910","title":"DataDream: Few-shot Guided Dataset Generation","created":"2024-07-15","cited_by_count":29},{"id":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28},{"id":"2410.19294","title":"Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting","created":"2024-10-25","cited_by_count":26},{"id":"2409.19375","title":"DOTA: Distributional Test-Time Adaptation of Vision-Language Models","created":"2024-09-28","cited_by_count":23},{"id":"2204.01186","title":"Revisiting a kNN-based Image Classification System with High-capacity Storage","created":"2022-04-03","cited_by_count":22},{"id":"2112.03162","title":"Embedding Arithmetic of Multimodal Queries for Image Retrieval","created":"2021-12-06","cited_by_count":21},{"id":"2310.10971","title":"Context-Aware Meta-Learning","created":"2023-10-17","cited_by_count":21},{"id":"2404.09447","title":"kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies","created":"2024-04-15","cited_by_count":20},{"id":"2112.13884","title":"A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision","created":"2021-12-27","cited_by_count":19},{"id":"2207.03784","title":"A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning","created":"2022-07-08","cited_by_count":19},{"id":"2211.03186","title":"Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning","created":"2022-11-06","cited_by_count":19},{"id":"2409.17805","title":"Cascade Prompt Learning for Vision-Language Model Adaptation","created":"2024-09-26","cited_by_count":19},{"id":"1908.02900","title":"iCassava 2019 Fine-Grained Visual Categorization Challenge","created":"2019-08-08","cited_by_count":17},{"id":"2302.11084","title":"Test-Time Distribution Normalization for Contrastively Learned Vision-language Models","created":"2023-02-22","cited_by_count":14},{"id":"2404.06244","title":"Anchor-based Robust Finetuning of Vision-Language Models","created":"2024-04-09","cited_by_count":11},{"id":"2405.01468","title":"Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models","created":"2024-05-02","cited_by_count":10},{"id":"2406.09384","title":"Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models","created":"2024-06-13","cited_by_count":8},{"id":"2408.08172","title":"Towards flexible perception with visual memory","created":"2024-08-15","cited_by_count":8},{"id":"2210.07396","title":"Caption supervision enables robust learners","created":"2022-10-13","cited_by_count":4},{"id":"2405.04782","title":"Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection","created":"2024-05-08","cited_by_count":4},{"id":"2410.08895","title":"Calibrated Cache Model for Few-Shot Vision-Language Model Adaptation","created":"2024-10-11","cited_by_count":3},{"id":"2404.09778","title":"The Devil is in the Few Shots: Iterative Visual Knowledge Completion for Few-shot Learning","created":"2024-04-15","cited_by_count":1}],"next_cursor":null}