{"list":"other","total":62,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"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":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"1703.07464","title":"No Fuss Distance Metric Learning using Proxies","created":"2017-03-21","cited_by_count":226},{"id":"2003.13911","title":"Proxy Anchor Loss for Deep Metric Learning","created":"2020-03-31","cited_by_count":195},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2203.10833","title":"Hyperbolic Vision Transformers: Combining Improvements in Metric Learning","created":"2022-03-21","cited_by_count":111},{"id":"2004.01113","title":"ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis","created":"2020-04-02","cited_by_count":107},{"id":"2210.04831","title":"Visual Prompt Tuning for Test-time Domain Adaptation","created":"2022-10-10","cited_by_count":97},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85},{"id":"2304.06648","title":"DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning","created":"2023-04-13","cited_by_count":84},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2303.08566","title":"Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning","created":"2023-03-15","cited_by_count":74},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"1908.01091","title":"Toward Understanding Catastrophic Forgetting in Continual Learning","created":"2019-08-02","cited_by_count":68},{"id":"2006.16362","title":"Multi-Head Attention: Collaborate Instead of Concatenate","created":"2020-06-29","cited_by_count":60},{"id":"2212.03220","title":"Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learning","created":"2022-12-06","cited_by_count":57},{"id":"2306.05067","title":"Improving Visual Prompt Tuning for Self-supervised Vision Transformers","created":"2023-06-08","cited_by_count":57},{"id":"2108.11179","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","created":"2021-08-25","cited_by_count":49},{"id":"2203.08547","title":"Non-isotropy Regularization for Proxy-based Deep Metric Learning","created":"2022-03-16","cited_by_count":33},{"id":"2402.02382","title":"Revisiting the Power of Prompt for Visual Tuning","created":"2024-02-04","cited_by_count":32},{"id":"2106.04990","title":"It Takes Two to Tango: Mixup for Deep Metric Learning","created":"2021-06-09","cited_by_count":23},{"id":"2302.00268","title":"Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection","created":"2023-02-01","cited_by_count":22},{"id":"2303.00198","title":"Convolutional Visual Prompt for Robust Visual Perception","created":"2023-03-01","cited_by_count":17},{"id":"2312.10376","title":"STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning","created":"2023-12-16","cited_by_count":17},{"id":"2307.11342","title":"Tuning Pre-trained Model via Moment Probing","created":"2023-07-21","cited_by_count":9},{"id":"2401.00617","title":"Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptation","created":"2024-01-01","cited_by_count":9},{"id":"2312.02923","title":"MoSA: Mixture of Sparse Adapters for Visual Efficient Tuning","created":"2023-12-05","cited_by_count":6},{"id":"2402.02340","title":"Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning","created":"2024-02-04","cited_by_count":6},{"id":"2010.12126","title":"Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization","created":"2020-10-23","cited_by_count":3}],"next_cursor":null}