{"total":113,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436,"area":null},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419,"area":null},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303,"area":null},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302,"area":null},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166,"area":null},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118,"area":null},{"id":"2210.01571","title":"VICRegL: Self-Supervised Learning of Local Visual Features","created":"2022-10-04","cited_by_count":118,"area":null},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115,"area":null},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99,"area":null},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2206.01204","title":"Siamese Image Modeling for Self-Supervised Vision Representation Learning","created":"2022-06-02","cited_by_count":78,"area":null},{"id":"2206.07706","title":"Masked Frequency Modeling for Self-Supervised Visual Pre-Training","created":"2022-06-15","cited_by_count":71,"area":null},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69,"area":null},{"id":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68,"area":null},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2210.07277","title":"The Hidden Uniform Cluster Prior in Self-Supervised Learning","created":"2022-10-13","cited_by_count":58,"area":null},{"id":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57,"area":null},{"id":"2303.14191","title":"Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning","created":"2023-03-24","cited_by_count":56,"area":null},{"id":"2208.00449","title":"SdAE: Self-distillated Masked Autoencoder","created":"2022-07-31","cited_by_count":52,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"area":null},{"id":"2208.04164","title":"Understanding Masked Image Modeling via Learning Occlusion Invariant Feature","created":"2022-08-08","cited_by_count":50,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2206.04664","title":"On Data Scaling in Masked Image Modeling","created":"2022-06-09","cited_by_count":46,"area":null},{"id":"2207.03208","title":"Revisiting Pretraining Objectives for Tabular Deep Learning","created":"2022-07-07","cited_by_count":43,"area":null},{"id":"2303.06697","title":"Traj-MAE: Masked Autoencoders for Trajectory Prediction","created":"2023-03-12","cited_by_count":42,"area":null},{"id":"2303.17152","title":"Mixed Autoencoder for Self-supervised Visual Representation Learning","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2307.07487","title":"DreamTeacher: Pretraining Image Backbones with Deep Generative Models","created":"2023-07-14","cited_by_count":37,"area":null},{"id":"2210.10615","title":"A Unified View of Masked Image Modeling","created":"2022-10-19","cited_by_count":36,"area":null},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34,"area":null},{"id":"2310.02980","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors","created":"2023-10-04","cited_by_count":34,"area":null},{"id":"2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","created":"2022-12-14","cited_by_count":33,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2205.13943","title":"Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN","created":"2022-05-27","cited_by_count":31,"area":null},{"id":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31,"area":null},{"id":"2211.08887","title":"Stare at What You See: Masked Image Modeling without Reconstruction","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2211.09799","title":"CAE v2: Context Autoencoder with CLIP Target","created":"2022-11-17","cited_by_count":25,"area":null},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2207.03860","title":"Consecutive Pretraining: A Knowledge Transfer Learning Strategy with Relevant Unlabeled Data for Remote Sensing Domain","created":"2022-07-08","cited_by_count":22,"area":null},{"id":"2210.07224","title":"Exploring Long-Sequence Masked Autoencoders","created":"2022-10-13","cited_by_count":22,"area":null},{"id":"2206.04667","title":"Extreme Masking for Learning Instance and Distributed Visual Representations","created":"2022-06-09","cited_by_count":21,"area":null},{"id":"2209.14389","title":"Downstream Datasets Make Surprisingly Good Pretraining Corpora","created":"2022-09-28","cited_by_count":20,"area":null},{"id":"2402.10093","title":"MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2203.12054","title":"Self-supervision through Random Segments with Autoregressive Coding (RandSAC)","created":"2022-03-22","cited_by_count":16,"area":null},{"id":"2304.13089","title":"Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations","created":"2023-04-25","cited_by_count":16,"area":null},{"id":"2406.09294","title":"You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2205.14338","title":"Object-wise Masked Autoencoders for Fast Pre-training","created":"2022-05-28","cited_by_count":15,"area":null},{"id":"2304.10520","title":"Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2311.01038","title":"Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2205.09904","title":"Deep transfer learning for image classification: a survey","created":"2022-05-20","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2303.11101","title":"Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning","created":"2023-03-20","cited_by_count":12,"area":null},{"id":"2407.18249","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","created":"2024-07-25","cited_by_count":10,"area":null},{"id":"2307.09361","title":"MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments","created":"2023-07-18","cited_by_count":9,"area":null},{"id":"2210.11016","title":"Towards Sustainable Self-supervised Learning","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2210.11404","title":"Self-Supervised Learning with Masked Image Modeling for Teeth Numbering, Detection of Dental Restorations, and Instance Segmentation in Dental Panoramic Radiographs","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2407.13036","title":"ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders","created":"2024-07-17","cited_by_count":8,"area":null},{"id":"2301.11915","title":"Understanding Self-Supervised Pretraining with Part-Aware Representation Learning","created":"2023-01-27","cited_by_count":7,"area":null},{"id":"2303.05370","title":"Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation","created":"2023-03-09","cited_by_count":7,"area":null},{"id":"2403.13808","title":"On Pretraining Data Diversity for Self-Supervised Learning","created":"2024-03-20","cited_by_count":7,"area":null},{"id":"2503.06960","title":"A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning","created":"2025-03-10","cited_by_count":7,"area":null},{"id":"2301.00230","title":"Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling","created":"2022-12-31","cited_by_count":6,"area":null},{"id":"2311.09104","title":"Cross-view and Cross-pose Completion for 3D Human Understanding","created":"2023-11-15","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":"2305.17271","title":"Robust Lane Detection through Self Pre-training with Masked Sequential Autoencoders and Fine-tuning with Customized PolyLoss","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2309.14136","title":"Masked Image Residual Learning for Scaling Deeper Vision Transformers","created":"2023-09-25","cited_by_count":5,"area":null},{"id":"2311.18557","title":"Can semi-supervised learning use all the data effectively? A lower bound perspective","created":"2023-11-30","cited_by_count":5,"area":null},{"id":"2401.00254","title":"Morphing Tokens Draw Strong Masked Image Models","created":"2023-12-30","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2306.07346","title":"Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2306.12070","title":"Task-Robust Pre-Training for Worst-Case Downstream Adaptation","created":"2023-06-21","cited_by_count":3,"area":null},{"id":"2310.13593","title":"Learning with Unmasked Tokens Drives Stronger Vision Learners","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2509.06990","title":"DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining","created":"2025-09-02","cited_by_count":3,"area":null},{"id":"2209.07474","title":"On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognition","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2210.00092","title":"Federated Training of Dual Encoding Models on Small Non-IID Client Datasets","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2302.08272","title":"Revisiting Hidden Representations in Transfer Learning for Medical Imaging","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2309.15313","title":"M$^{3}$3D: Learning 3D priors using Multi-Modal Masked Autoencoders for 2D image and video understanding","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2311.03149","title":"Asymmetric Masked Distillation for Pre-Training Small Foundation Models","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2312.04398","title":"Intelligent Anomaly Detection for Lane Rendering Using Transformer with Self-Supervised Pre-Training and Customized Fine-Tuning","created":"2023-12-07","cited_by_count":2,"area":null},{"id":"2405.01590","title":"101 Billion Arabic Words Dataset","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2410.07442","title":"Self-Supervised Learning for Real-World Object Detection: a Survey","created":"2024-10-09","cited_by_count":2,"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":"2303.04664","title":"Centroid-centered Modeling for Efficient Vision Transformer Pre-training","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2303.08481","title":"SeqCo-DETR: Sequence Consistency Training for Self-Supervised Object Detection with Transformers","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2403.05220","title":"Synthetic Privileged Information Enhances Medical Image Representation Learning","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2405.06636","title":"Federated Document Visual Question Answering: A Pilot Study","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2412.17566","title":"The Dynamic Duo of Collaborative Masking and Target for Advanced Masked Autoencoder Learning","created":"2024-12-23","cited_by_count":1,"area":null}],"next_cursor":"100"}