{"total":203,"rows":[{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"area":null},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"id":"2306.12873","title":"FuXi: A cascade machine learning forecasting system for 15-day global weather forecast","created":"2023-06-22","cited_by_count":241,"area":null},{"id":"2111.11429","title":"Benchmarking Detection Transfer Learning with Vision Transformers","created":"2021-11-22","cited_by_count":131,"area":null},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100,"area":null},{"id":"2104.14726","title":"MOOD: Multi-level Out-of-distribution Detection","created":"2021-04-30","cited_by_count":94,"area":null},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2106.07477","title":"S$^2$-MLP: Spatial-Shift MLP Architecture for Vision","created":"2021-06-14","cited_by_count":83,"area":null},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70,"area":null},{"id":"2106.04781","title":"Encoding physics to learn reaction-diffusion processes","created":"2021-06-09","cited_by_count":61,"area":null},{"id":"2307.02764","title":"When Does Confidence-Based Cascade Deferral Suffice?","created":"2023-07-06","cited_by_count":60,"area":null},{"id":"2403.11270","title":"Bilateral Propagation Network for Depth Completion","created":"2024-03-17","cited_by_count":60,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2211.11436","title":"N-Gram in Swin Transformers for Efficient Lightweight Image Super-Resolution","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46,"area":null},{"id":"2112.12089","title":"Reflash Dropout in Image Super-Resolution","created":"2021-12-22","cited_by_count":41,"area":null},{"id":"2109.05422","title":"Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?","created":"2021-09-12","cited_by_count":38,"area":null},{"id":"2210.06778","title":"X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2412.09586","title":"Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders","created":"2024-12-12","cited_by_count":36,"area":null},{"id":"2101.01761","title":"AutoDropout: Learning Dropout Patterns to Regularize Deep Networks","created":"2021-01-05","cited_by_count":35,"area":null},{"id":"2109.05489","title":"Illuminating Diverse Neural Cellular Automata for Level Generation","created":"2021-09-12","cited_by_count":35,"area":null},{"id":"2103.05471","title":"Contrastive Neural Architecture Search with Neural Architecture Comparators","created":"2021-03-08","cited_by_count":34,"area":null},{"id":"2304.09856","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","created":"2023-04-19","cited_by_count":34,"area":null},{"id":"2404.00801","title":"$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding","created":"2024-03-31","cited_by_count":34,"area":null},{"id":"2106.00149","title":"HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization","created":"2021-05-31","cited_by_count":32,"area":null},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2203.09176","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation","created":"2022-03-17","cited_by_count":27,"area":null},{"id":"2110.03091","title":"Improving Fractal Pre-training","created":"2021-10-06","cited_by_count":26,"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":"2108.06208","title":"LT-OCF: Learnable-Time ODE-based Collaborative Filtering","created":"2021-08-08","cited_by_count":21,"area":null},{"id":"2303.01500","title":"Dropout Reduces Underfitting","created":"2023-03-02","cited_by_count":21,"area":null},{"id":"2411.18933","title":"Efficient Track Anything","created":"2024-11-28","cited_by_count":21,"area":null},{"id":"2106.15941","title":"Augmented Shortcuts for Vision Transformers","created":"2021-06-30","cited_by_count":19,"area":null},{"id":"2108.04603","title":"Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2303.15270","title":"Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling","created":"2023-03-27","cited_by_count":19,"area":null},{"id":"2310.19182","title":"Fast Trainable Projection for Robust Fine-Tuning","created":"2023-10-29","cited_by_count":19,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2212.00057","title":"Part-based Face Recognition with Vision Transformers","created":"2022-11-30","cited_by_count":18,"area":null},{"id":"2306.17319","title":"ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation","created":"2023-06-29","cited_by_count":18,"area":null},{"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":"2106.02694","title":"Efficient Classification of Very Large Images with Tiny Objects","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2405.11582","title":"SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalization","created":"2024-05-19","cited_by_count":17,"area":null},{"id":"2108.08467","title":"Medical Image Segmentation with 3D Convolutional Neural Networks: A Survey","created":"2021-08-19","cited_by_count":16,"area":null},{"id":"2308.04522","title":"Deep Learning for Steganalysis of Diverse Data Types: A review of methods, taxonomy, challenges and future directions","created":"2023-08-08","cited_by_count":16,"area":null},{"id":"2406.10973","title":"ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts","created":"2024-06-16","cited_by_count":16,"area":null},{"id":"2106.14882","title":"Rethinking Token-Mixing MLP for MLP-based Vision Backbone","created":"2021-06-28","cited_by_count":15,"area":null},{"id":"2110.07641","title":"Non-deep Networks","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2303.07806","title":"USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation","created":"2023-03-14","cited_by_count":14,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2104.02308","title":"ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2209.11750","title":"Transformer-based Models to Deal with Heterogeneous Environments in Human Activity Recognition","created":"2022-09-22","cited_by_count":12,"area":null},{"id":"2104.04946","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","created":"2021-04-11","cited_by_count":11,"area":null},{"id":"2511.07329","title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","created":"2025-11-10","cited_by_count":11,"area":null},{"id":"2201.12903","title":"Aggregating Global Features into Local Vision Transformer","created":"2022-01-30","cited_by_count":10,"area":null},{"id":"2310.11959","title":"A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2411.17662","title":"RoboPEPP: Vision-Based Robot Pose and Joint Angle Estimation through Embedding Predictive Pre-Training","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2505.01571","title":"PainFormer: a Vision Foundation Model for Automatic Pain Assessment","created":"2025-05-02","cited_by_count":10,"area":null},{"id":"2108.04993","title":"LightMove: A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising","created":"2021-08-11","cited_by_count":9,"area":null},{"id":"2206.15015","title":"Exploring Temporally Dynamic Data Augmentation for Video Recognition","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2310.07361","title":"Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters","created":"2023-10-11","cited_by_count":9,"area":null},{"id":"2406.07543","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2411.01713","title":"Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models","created":"2024-11-03","cited_by_count":9,"area":null},{"id":"2211.12386","title":"A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms","created":"2022-11-22","cited_by_count":8,"area":null},{"id":"2403.17016","title":"HEAL-ViT: Vision Transformers on a spherical mesh for medium-range weather forecasting","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2503.14125","title":"Frac-Connections: Fractional Extension of Hyper-Connections","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2205.06265","title":"ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training","created":"2022-05-12","cited_by_count":7,"area":null},{"id":"2212.06735","title":"POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification","created":"2022-12-13","cited_by_count":7,"area":null},{"id":"2408.05749","title":"Efficient and Versatile Robust Fine-Tuning of Zero-shot Models","created":"2024-08-11","cited_by_count":7,"area":null},{"id":"2102.09808","title":"Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss","created":"2021-02-19","cited_by_count":6,"area":null},{"id":"2106.02859","title":"Convolutional Neural Networks with Gated Recurrent Connections","created":"2021-06-05","cited_by_count":6,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2111.04670","title":"Approximate Neural Architecture Search via Operation Distribution Learning","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2112.07441","title":"An Interpretive Constrained Linear Model for ResNet and MgNet","created":"2021-12-14","cited_by_count":6,"area":null},{"id":"2207.09339","title":"Vision Transformers: From Semantic Segmentation to Dense Prediction","created":"2022-07-19","cited_by_count":6,"area":null},{"id":"2209.08667","title":"Semantic Segmentation using Neural Ordinary Differential Equations","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2301.04608","title":"Padding Module: Learning the Padding in Deep Neural Networks","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2302.14772","title":"PA&DA: Jointly Sampling PAth and DAta for Consistent NAS","created":"2023-02-28","cited_by_count":6,"area":null},{"id":"2305.02507","title":"Stimulative Training++: Go Beyond The Performance Limits of Residual Networks","created":"2023-05-04","cited_by_count":6,"area":null},{"id":"2405.07395","title":"CaFA: Global Weather Forecasting with Factorized Attention on Sphere","created":"2024-05-12","cited_by_count":6,"area":null},{"id":"2102.01963","title":"Local Critic Training for Model-Parallel Learning of Deep Neural Networks","created":"2021-02-03","cited_by_count":5,"area":null},{"id":"2103.05342","title":"Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network","created":"2021-03-09","cited_by_count":5,"area":null},{"id":"2105.03155","title":"Diffusion Mechanism in Residual Neural Network: Theory and Applications","created":"2021-05-07","cited_by_count":5,"area":null},{"id":"2110.10536","title":"Improving Model Generalization by Agreement of Learned Representations from Data Augmentation","created":"2021-10-20","cited_by_count":5,"area":null},{"id":"2208.11718","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","created":"2022-08-24","cited_by_count":5,"area":null},{"id":"2106.15778","title":"Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification","created":"2021-06-30","cited_by_count":4,"area":null},{"id":"2201.03013","title":"ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections","created":"2022-01-09","cited_by_count":4,"area":null},{"id":"2203.05508","title":"Towards Less Constrained Macro-Neural Architecture Search","created":"2022-03-10","cited_by_count":4,"area":null},{"id":"2204.02027","title":"A Survey on Dropout Methods and Experimental Verification in Recommendation","created":"2022-04-05","cited_by_count":4,"area":null},{"id":"2209.10909","title":"Vanilla Feedforward Neural Networks as a Discretization of Dynamical Systems","created":"2022-09-22","cited_by_count":4,"area":null},{"id":"2301.12592","title":"Ensemble Learning for Fusion of Multiview Vision with Occlusion and Missing Information: Framework and Evaluations with Real-World Data and Applications in Driver Hand Activity Recognition","created":"2023-01-30","cited_by_count":4,"area":null},{"id":"2407.06964","title":"Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach","created":"2024-07-09","cited_by_count":4,"area":null},{"id":"2408.09408","title":"VrdONE: One-stage Video Visual Relation Detection","created":"2024-08-18","cited_by_count":4,"area":null},{"id":"2411.03042","title":"Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning","created":"2024-11-05","cited_by_count":4,"area":null},{"id":"2506.09714","title":"Auto-Compressing Networks","created":"2025-06-11","cited_by_count":4,"area":null}],"next_cursor":"100"}