{"total":108,"rows":[{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375,"area":null},{"id":"2112.10740","title":"Are Large-scale Datasets Necessary for Self-Supervised Pre-training?","created":"2021-12-20","cited_by_count":117,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2301.11706","title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","created":"2023-01-27","cited_by_count":90,"area":"diffusion"},{"id":"2210.10732","title":"OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping","created":"2022-10-19","cited_by_count":82,"area":null},{"id":"2303.15446","title":"SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications","created":"2023-03-27","cited_by_count":66,"area":null},{"id":"2305.09828","title":"Mimetic Initialization of Self-Attention Layers","created":"2023-05-16","cited_by_count":54,"area":null},{"id":"2205.15463","title":"Few-Shot Diffusion Models","created":"2022-05-30","cited_by_count":38,"area":"diffusion"},{"id":"2303.06818","title":"Backdoor Defense via Deconfounded Representation Learning","created":"2023-03-13","cited_by_count":38,"area":null},{"id":"2206.07267","title":"Rethinking Generalization in Few-Shot Classification","created":"2022-06-15","cited_by_count":36,"area":null},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35,"area":null},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34,"area":null},{"id":"2205.12551","title":"Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers","created":"2022-05-25","cited_by_count":33,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2207.10026","title":"Locality Guidance for Improving Vision Transformers on Tiny Datasets","created":"2022-07-20","cited_by_count":33,"area":null},{"id":"2210.05958","title":"Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets","created":"2022-10-12","cited_by_count":29,"area":null},{"id":"2302.03751","title":"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective","created":"2023-02-07","cited_by_count":28,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2409.08573","title":"HTR-VT: Handwritten Text Recognition with Vision Transformer","created":"2024-09-13","cited_by_count":24,"area":null},{"id":"2503.01835","title":"Primus: Enforcing Attention Usage for 3D Medical Image Segmentation","created":"2025-03-03","cited_by_count":24,"area":null},{"id":"2202.05054","title":"Exploiting Spatial Sparsity for Event Cameras with Visual Transformers","created":"2022-02-10","cited_by_count":23,"area":null},{"id":"2303.15466","title":"Supervised Masked Knowledge Distillation for Few-Shot Transformers","created":"2023-03-25","cited_by_count":23,"area":"distill"},{"id":"2203.07057","title":"Self-Promoted Supervision for Few-Shot Transformer","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2408.14080","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","created":"2024-08-26","cited_by_count":21,"area":null},{"id":"2203.03990","title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","created":"2022-03-08","cited_by_count":20,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2211.10686","title":"Spikeformer: A Novel Architecture for Training High-Performance Low-Latency Spiking Neural Network","created":"2022-11-19","cited_by_count":19,"area":null},{"id":"2310.07265","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":"distill"},{"id":"2311.05613","title":"Window Attention is Bugged: How not to Interpolate Position Embeddings","created":"2023-11-09","cited_by_count":18,"area":null},{"id":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","cited_by_count":18,"area":null},{"id":"2212.13805","title":"Swin MAE: Masked Autoencoders for Small Datasets","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2310.20704","title":"Limited Data, Unlimited Potential: A Study on ViTs Augmented by Masked Autoencoders","created":"2023-10-31","cited_by_count":17,"area":null},{"id":"2210.12333","title":"Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2401.10458","title":"Contrastive Unlearning: A Contrastive Approach to Machine Unlearning","created":"2024-01-19","cited_by_count":15,"area":"safety"},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2205.14794","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","created":"2022-05-30","cited_by_count":13,"area":null},{"id":"2403.10519","title":"Frozen Feature Augmentation for Few-Shot Image Classification","created":"2024-03-15","cited_by_count":13,"area":null},{"id":"2312.06733","title":"TULIP: Transformer for Upsampling of LiDAR Point Clouds","created":"2023-12-11","cited_by_count":12,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"area":null},{"id":"2405.15495","title":"Towards Natural Machine Unlearning","created":"2024-05-24","cited_by_count":11,"area":"safety"},{"id":"2307.02100","title":"MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets","created":"2023-07-05","cited_by_count":9,"area":null},{"id":"2502.06832","title":"Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach","created":"2025-02-05","cited_by_count":8,"area":"moe"},{"id":"2312.02843","title":"Are Vision Transformers More Data Hungry Than Newborn Visual Systems?","created":"2023-12-05","cited_by_count":7,"area":null},{"id":"2211.05187","title":"Training a Vision Transformer from scratch in less than 24 hours with 1 GPU","created":"2022-11-09","cited_by_count":6,"area":null},{"id":"2303.15553","title":"MoViT: Memorizing Vision Transformers for Medical Image Analysis","created":"2023-03-27","cited_by_count":6,"area":null},{"id":"2304.05350","title":"Astroformer: More Data Might not be all you need for Classification","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2305.08551","title":"Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation","created":"2023-05-15","cited_by_count":6,"area":null},{"id":"2311.03873","title":"Mini but Mighty: Finetuning ViTs with Mini Adapters","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2408.14131","title":"GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasets","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2502.20760","title":"VRM: Knowledge Distillation via Virtual Relation Matching","created":"2025-02-28","cited_by_count":6,"area":"distill"},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2204.04788","title":"Representation Learning by Detecting Incorrect Location Embeddings","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2206.04636","title":"Spatial Entropy as an Inductive Bias for Vision Transformers","created":"2022-06-09","cited_by_count":5,"area":null},{"id":"2209.09735","title":"Relaxed Attention for Transformer Models","created":"2022-09-20","cited_by_count":5,"area":null},{"id":"2508.00367","title":"Representation Shift: Unifying Token Compression with FlashAttention","created":"2025-08-01","cited_by_count":5,"area":"inference"},{"id":"2212.14215","title":"Local Learning on Transformers via Feature Reconstruction","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2304.07728","title":"TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation","created":"2023-04-16","cited_by_count":4,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","cited_by_count":4,"area":null},{"id":"2401.12511","title":"Convolutional Initialization for Data-Efficient Vision Transformers","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2404.01139","title":"Structured Initialization for Attention in Vision Transformers","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2507.18424","title":"Self-Supervised Ultrasound-Video Segmentation with Feature Prediction and 3D Localised Loss","created":"2025-07-24","cited_by_count":4,"area":null},{"id":"2208.04693","title":"How Well Do Vision Transformers (VTs) Transfer To The Non-Natural Image Domain? An Empirical Study Involving Art Classification","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2402.16674","title":"ConSept: Continual Semantic Segmentation via Adapter-based Vision Transformer","created":"2024-02-26","cited_by_count":3,"area":null},{"id":"2403.06289","title":"Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning","created":"2024-03-10","cited_by_count":3,"area":null},{"id":"2409.02545","title":"UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2409.05785","title":"NeurLZ: An Online Neural Learning-Based Method to Enhance Scientific Lossy Compression","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2409.19582","title":"Self-supervised Auxiliary Learning for Texture and Model-based Hybrid Robust and Fair Featuring in Face Analysis","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2509.08959","title":"CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2311.16481","title":"Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning","created":"2023-11-25","cited_by_count":2,"area":null},{"id":"2406.13963","title":"SSAD: Self-supervised Auxiliary Detection Framework for Panoramic X-ray based Dental Disease Diagnosis","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.13920","title":"DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.17370","title":"The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2501.06040","title":"MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2510.00283","title":"Data driven approaches in nanophotonics: A review of AI-enabled metadevices","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2206.12925","title":"Vision Transformer for Contrastive Clustering","created":"2022-06-26","cited_by_count":1,"area":null},{"id":"2207.04399","title":"Horizontal and Vertical Attention in Transformers","created":"2022-07-10","cited_by_count":1,"area":null},{"id":"2207.04403","title":"Self-attention on Multi-Shifted Windows for Scene Segmentation","created":"2022-07-10","cited_by_count":1,"area":null},{"id":"2210.12599","title":"Transformers For Recognition In Overhead Imagery: A Reality Check","created":"2022-10-23","cited_by_count":1,"area":null},{"id":"2210.14319","title":"Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2212.05677","title":"Masked autoencoders are effective solution to transformer data-hungry","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2308.09455","title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2309.05375","title":"Toward a Deeper Understanding: RetNet Viewed through Convolution","created":"2023-09-11","cited_by_count":1,"area":null},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1,"area":null},{"id":"2501.06220","title":"Powerful Design of Small Vision Transformer on CIFAR10","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2502.06192","title":"Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation","created":"2025-02-10","cited_by_count":1,"area":"distill"},{"id":"2502.14184","title":"Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2509.24115","title":"ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2512.04723","title":"CIG-MAE: Cross-Modal Information-Guided Masked Autoencoder for Self-Supervised WiFi Sensing","created":"2025-12-04","cited_by_count":1,"area":null},{"id":"2512.11507","title":"SSA3D: Text-Conditioned Assisted Self-Supervised Framework for Automatic Dental Abutment Design","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2605.09850","title":"Probing Routing-Conditional Calibration in Attention-Residual Transformers","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2306.01423","title":"Break a Lag: Triple Exponential Moving Average for Enhanced Optimization","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2310.17176","title":"A Deep Learning Approach to Teeth Segmentation and Orientation from Panoramic X-rays","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2404.04924","title":"GvT: A Graph-based Vision Transformer with Talking-Heads Utilizing Sparsity, Trained from Scratch on Small Datasets","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2406.01337","title":"ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2503.04121","title":"Simple Self Organizing Map with Vision Transformers","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2505.13137","title":"Learning to Adapt to Position Bias in Vision Transformer Classifiers","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.12982","title":"DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2509.20501","title":"Beyond Visual Similarity: Rule-Guided Multimodal Clustering with explicit domain rules","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2601.12051","title":"A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models","created":"2026-01-17","cited_by_count":0,"area":null}],"next_cursor":"100"}