{"list":"other","total":65,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"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":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2303.08138","title":"Diversity-Aware Meta Visual Prompting","created":"2023-03-14","cited_by_count":58},{"id":"2306.05067","title":"Improving Visual Prompt Tuning for Self-supervised Vision Transformers","created":"2023-06-08","cited_by_count":57},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43},{"id":"1907.04377","title":"Convergence Rates for Gaussian Mixtures of Experts","created":"2019-07-09","cited_by_count":39},{"id":"2305.03288","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","created":"2023-05-05","cited_by_count":33},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31},{"id":"2305.18787","title":"Universality and Limitations of Prompt Tuning","created":"2023-05-30","cited_by_count":30},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30},{"id":"2405.13997","title":"Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts","created":"2024-05-22","cited_by_count":24},{"id":"2402.02952","title":"On Least Square Estimation in Softmax Gating Mixture of Experts","created":"2024-02-05","cited_by_count":23},{"id":"2202.08786","title":"Refined Convergence Rates for Maximum Likelihood Estimation under Finite Mixture Models","created":"2022-02-17","cited_by_count":22},{"id":"2312.10376","title":"STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning","created":"2023-12-16","cited_by_count":17},{"id":"2401.13875","title":"Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?","created":"2024-01-25","cited_by_count":15},{"id":"2410.02200","title":"Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts","created":"2024-10-03","cited_by_count":15},{"id":"2311.12048","title":"One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning","created":"2023-11-18","cited_by_count":8},{"id":"2412.08285","title":"Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective","created":"2024-12-11","cited_by_count":6},{"id":"2408.14961","title":"CVPT: Cross Visual Prompt Tuning","created":"2024-08-27","cited_by_count":2},{"id":"2409.05312","title":"Open-World Dynamic Prompt and Continual Visual Representation Learning","created":"2024-09-09","cited_by_count":2}],"next_cursor":null}