{"total":146,"rows":[{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446,"area":null},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135,"area":null},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999,"area":null},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"area":null},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628,"area":null},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2110.06207","title":"Open-Set Recognition: a Good Closed-Set Classifier is All You Need?","created":"2021-10-12","cited_by_count":353,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106,"area":null},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104,"area":null},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2106.04015","title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","created":"2021-06-07","cited_by_count":82,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"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":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68,"area":null},{"id":"2403.13043","title":"When Do We Not Need Larger Vision Models?","created":"2024-03-19","cited_by_count":67,"area":null},{"id":"2204.12511","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","created":"2022-04-26","cited_by_count":63,"area":null},{"id":"2203.01825","title":"What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2205.07514","title":"Residual Local Feature Network for Efficient Super-Resolution","created":"2022-05-16","cited_by_count":53,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2203.02557","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","created":"2022-03-04","cited_by_count":42,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2302.01738","title":"AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge","created":"2023-02-03","cited_by_count":35,"area":null},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34,"area":null},{"id":"2201.11279","title":"Revisiting RCAN: Improved Training for Image Super-Resolution","created":"2022-01-27","cited_by_count":32,"area":null},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"area":null},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2205.14612","title":"Do Residual Neural Networks discretize Neural Ordinary Differential Equations?","created":"2022-05-29","cited_by_count":27,"area":null},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2305.13456","title":"Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matters","created":"2023-05-22","cited_by_count":27,"area":null},{"id":"2202.01653","title":"Learning strides in convolutional neural networks","created":"2022-02-03","cited_by_count":26,"area":null},{"id":"2210.09943","title":"Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition","created":"2022-10-18","cited_by_count":26,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2301.11990","title":"Alignment with human representations supports robust few-shot learning","created":"2023-01-27","cited_by_count":25,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2211.16421","title":"RGB no more: Minimally-decoded JPEG Vision Transformers","created":"2022-11-29","cited_by_count":18,"area":null},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2111.09451","title":"Benchmarking and scaling of deep learning models for land cover image classification","created":"2021-11-18","cited_by_count":14,"area":null},{"id":"2110.11852","title":"Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation","created":"2021-10-22","cited_by_count":13,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2303.07034","title":"Pretrained ViTs Yield Versatile Representations For Medical Images","created":"2023-03-13","cited_by_count":13,"area":null},{"id":"2402.06994","title":"A Change Detection Reality Check","created":"2024-02-10","cited_by_count":13,"area":null},{"id":"2403.19588","title":"DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs","created":"2024-03-28","cited_by_count":12,"area":null},{"id":"2109.01696","title":"Revisiting 3D ResNets for Video Recognition","created":"2021-09-03","cited_by_count":10,"area":null},{"id":"2106.03485","title":"Redundant representations help generalization in wide neural networks","created":"2021-06-07","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":"2207.03807","title":"Beyond Transfer Learning: Co-finetuning for Action Localisation","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2303.16280","title":"UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2107.05202","title":"Delta Sampling R-BERT for limited data and low-light action recognition","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2302.06112","title":"How to Use Dropout Correctly on Residual Networks with Batch Normalization","created":"2023-02-13","cited_by_count":7,"area":null},{"id":"2104.03577","title":"Stable deep neural network architectures for mitochondria segmentation on electron microscopy volumes","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"area":null},{"id":"2204.00853","title":"Adversarial Neon Beam: A Light-based Physical Attack to DNNs","created":"2022-04-02","cited_by_count":6,"area":null},{"id":"2204.01209","title":"EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2301.05158","title":"SemPPL: Predicting pseudo-labels for better contrastive representations","created":"2023-01-12","cited_by_count":6,"area":null},{"id":"2509.23383","title":"Train Once, Answer All: Many Pretraining Experiments for the Cost of One","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2106.10771","title":"Multirate Training of Neural Networks","created":"2021-06-20","cited_by_count":5,"area":null},{"id":"2202.02777","title":"Learning Features with Parameter-Free Layers","created":"2022-02-06","cited_by_count":5,"area":null},{"id":"2206.15274","title":"Augment like there's no tomorrow: Consistently performing neural networks for medical imaging","created":"2022-06-30","cited_by_count":5,"area":null},{"id":"2209.06692","title":"FreeGaze: Resource-efficient Gaze Estimation via Frequency Domain Contrastive Learning","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2212.09408","title":"Universal Object Detection with Large Vision Model","created":"2022-12-19","cited_by_count":5,"area":null},{"id":"2306.00985","title":"Using generative AI to investigate medical imagery models and datasets","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2106.05795","title":"Transformed CNNs: recasting pre-trained convolutional layers with self-attention","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2304.02122","title":"OpenContrails: Benchmarking Contrail Detection on GOES-16 ABI","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2305.19688","title":"VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2401.08505","title":"Harnessing Orthogonality to Train Low-Rank Neural Networks","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2103.15244","title":"Rethinking ResNets: Improved Stacking Strategies With High Order Schemes","created":"2021-03-28","cited_by_count":3,"area":null},{"id":"2205.01142","title":"Cost-Aware Evaluation and Model Scaling for LiDAR-Based 3D Object Detection","created":"2022-05-02","cited_by_count":3,"area":null},{"id":"2206.12458","title":"Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images","created":"2022-06-24","cited_by_count":3,"area":null},{"id":"2212.12552","title":"A Close Look at Spatial Modeling: From Attention to Convolution","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2406.11463","title":"Just How Flexible are Neural Networks in Practice?","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2108.00177","title":"Greedy Network Enlarging","created":"2021-07-31","cited_by_count":2,"area":null},{"id":"2111.12787","title":"Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator","created":"2021-11-24","cited_by_count":2,"area":null},{"id":"2207.11511","title":"SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling","created":"2022-07-23","cited_by_count":2,"area":null},{"id":"2304.09067","title":"Performance of GAN-based augmentation for deep learning COVID-19 image classification","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2308.12492","title":"Optimizing Neural Network Scale for ECG Classification","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2504.10735","title":"Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null}],"next_cursor":"100"}