{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"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":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2004.08790","title":"UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation","created":"2020-04-19","cited_by_count":332},{"id":"1904.05835","title":"Variational Information Distillation for Knowledge Transfer","created":"2019-04-11","cited_by_count":324},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2010.15327","title":"Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth","created":"2020-10-29","cited_by_count":245},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212},{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"1708.07632","title":"Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition","created":"2017-08-25","cited_by_count":178},{"id":"1905.00076","title":"Ensemble Distribution Distillation","created":"2019-04-30","cited_by_count":158},{"id":"2012.03236","title":"Cross-Layer Distillation with Semantic Calibration","created":"2020-12-06","cited_by_count":143},{"id":"2306.05705","title":"On the Challenges and Perspectives of Foundation Models for Medical Image Analysis","created":"2023-06-09","cited_by_count":135},{"id":"2204.06986","title":"Cross-Image Relational Knowledge Distillation for Semantic Segmentation","created":"2022-04-14","cited_by_count":118},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107},{"id":"2005.06465","title":"MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset","created":"2020-05-13","cited_by_count":104},{"id":"2003.11597","title":"COVID-19 Image Data Collection","created":"2020-03-25","cited_by_count":101},{"id":"2003.13865","title":"COVID-CT-Dataset: A CT Scan Dataset about COVID-19","created":"2020-03-30","cited_by_count":94},{"id":"2108.11195","title":"Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification","created":"2021-08-25","cited_by_count":89},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81},{"id":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76},{"id":"2210.01033","title":"LPT: Long-tailed Prompt Tuning for Image Classification","created":"2022-10-03","cited_by_count":69},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2305.03937","title":"Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization","created":"2023-05-06","cited_by_count":64},{"id":"2306.11925","title":"LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching","created":"2023-06-20","cited_by_count":60},{"id":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","cited_by_count":57},{"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":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39},{"id":"2303.06274","title":"CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting","created":"2023-03-11","cited_by_count":33},{"id":"2311.08236","title":"MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis","created":"2023-11-14","cited_by_count":33},{"id":"2102.09528","title":"Image Compositing for Segmentation of Surgical Tools without Manual Annotations","created":"2021-02-18","cited_by_count":23},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12},{"id":"2304.02263","title":"Towards Efficient Task-Driven Model Reprogramming with Foundation Models","created":"2023-04-05","cited_by_count":5},{"id":"2404.17184","title":"Low-Rank Knowledge Decomposition for Medical Foundation Models","created":"2024-04-26","cited_by_count":5},{"id":"2407.06504","title":"Reprogramming Distillation for Medical Foundation Models","created":"2024-07-09","cited_by_count":5},{"id":"2409.19540","title":"LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models","created":"2024-09-29","cited_by_count":4}],"next_cursor":null}