{"list":"other","total":54,"rows":[{"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":"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":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"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":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"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":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117},{"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":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83},{"id":"1709.02480","title":"Fine-Grained Car Detection for Visual Census Estimation","created":"2017-09-07","cited_by_count":76},{"id":"2302.08106","title":"Towards Efficient Visual Adaption via Structural Re-parameterization","created":"2023-02-16","cited_by_count":73},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"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":"2207.14381","title":"Pro-tuning: Unified Prompt Tuning for Vision Tasks","created":"2022-07-28","cited_by_count":53},{"id":"2403.01439","title":"Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis","created":"2024-03-03","cited_by_count":53},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44},{"id":"2201.03014","title":"Glance and Focus Networks for Dynamic Visual Recognition","created":"2022-01-09","cited_by_count":41},{"id":"2304.01917","title":"Strong Baselines for Parameter Efficient Few-Shot Fine-tuning","created":"2023-04-04","cited_by_count":37},{"id":"2310.06234","title":"Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing","created":"2023-10-10","cited_by_count":35},{"id":"2310.19859","title":"Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone","created":"2023-10-30","cited_by_count":26},{"id":"2403.11808","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","created":"2024-03-18","cited_by_count":25},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24},{"id":"2303.09992","title":"LION: Implicit Vision Prompt Tuning","created":"2023-03-17","cited_by_count":22},{"id":"2312.07856","title":"DTL: Disentangled Transfer Learning for Visual Recognition","created":"2023-12-13","cited_by_count":22},{"id":"2303.15591","title":"Learning Expressive Prompting With Residuals for Vision Transformers","created":"2023-03-27","cited_by_count":21},{"id":"2309.08513","title":"SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels","created":"2023-09-15","cited_by_count":20},{"id":"2403.19067","title":"Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach","created":"2024-03-28","cited_by_count":18},{"id":"2309.06922","title":"Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuning","created":"2023-09-13","cited_by_count":17},{"id":"2406.06820","title":"Adapters Strike Back","created":"2024-06-10","cited_by_count":16},{"id":"2406.03051","title":"Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision","created":"2024-06-05","cited_by_count":13},{"id":"2211.16726","title":"Boosted Dynamic Neural Networks","created":"2022-11-30","cited_by_count":8},{"id":"2402.04009","title":"Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning","created":"2024-02-06","cited_by_count":7},{"id":"2407.14302","title":"Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition","created":"2024-07-19","cited_by_count":3}],"next_cursor":null}