{"list":"other","total":100,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1705.07057","title":"Masked Autoregressive Flow for Density Estimation","created":"2017-05-19","cited_by_count":684},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"1806.08342","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","created":"2018-06-21","cited_by_count":521},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1811.00995","title":"Invertible Residual Networks","created":"2018-11-02","cited_by_count":365},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1502.03509","title":"MADE: Masked Autoencoder for Distribution Estimation","created":"2015-02-12","cited_by_count":307},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"2104.07857","title":"ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning","created":"2021-04-16","cited_by_count":256},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1707.04585","title":"The Reversible Residual Network: Backpropagation Without Storing Activations","created":"2017-07-14","cited_by_count":217},{"id":"1904.04514","title":"High-Resolution Representations for Labeling Pixels and Regions","created":"2019-04-09","cited_by_count":211},{"id":"1804.00779","title":"Neural Autoregressive Flows","created":"2018-04-03","cited_by_count":208},{"id":"2005.10821","title":"Hierarchical Multi-Scale Attention for Semantic Segmentation","created":"2020-05-21","cited_by_count":183},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"1802.07088","title":"i-RevNet: Deep Invertible Networks","created":"2018-02-20","cited_by_count":137},{"id":"2003.13630","title":"TResNet: High Performance GPU-Dedicated Architecture","created":"2020-03-30","cited_by_count":119},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98},{"id":"1910.02653","title":"Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization","created":"2019-10-07","cited_by_count":91},{"id":"1606.03401","title":"Memory-Efficient Backpropagation Through Time","created":"2016-06-10","cited_by_count":78},{"id":"1910.05124","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","created":"2019-10-09","cited_by_count":55},{"id":"2103.06877","title":"Fast and Accurate Model Scaling","created":"2021-03-11","cited_by_count":46},{"id":"1511.05950","title":"Staleness-aware Async-SGD for Distributed Deep Learning","created":"2015-11-18","cited_by_count":43},{"id":"1907.11818","title":"Momentum-Net: Fast and convergent iterative neural network for inverse problems","created":"2019-07-26","cited_by_count":38},{"id":"2102.07870","title":"Momentum Residual Neural Networks","created":"2021-02-15","cited_by_count":37},{"id":"1905.05894","title":"Online Normalization for Training Neural Networks","created":"2019-05-15","cited_by_count":29},{"id":"1809.02839","title":"Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform","created":"2018-09-08","cited_by_count":28},{"id":"1810.10999","title":"Reversible Recurrent Neural Networks","created":"2018-10-25","cited_by_count":23},{"id":"2008.01531","title":"TOAD-GAN: Coherent Style Level Generation from a Single Example","created":"2020-08-04","cited_by_count":22},{"id":"1806.02479","title":"Interlinked Convolutional Neural Networks for Face Parsing","created":"2018-06-07","cited_by_count":16},{"id":"1906.06148","title":"A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation","created":"2019-06-14","cited_by_count":16},{"id":"2110.07641","title":"Non-deep Networks","created":"2021-10-14","cited_by_count":14},{"id":"2105.14669","title":"Memory-Efficient Differentiable Transformer Architecture Search","created":"2021-05-31","cited_by_count":13},{"id":"2011.07248","title":"Self Normalizing Flows","created":"2020-11-14","cited_by_count":12},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12},{"id":"2003.11666","title":"Pipelined Backpropagation at Scale: Training Large Models without Batches","created":"2020-03-25","cited_by_count":11},{"id":"1803.09926","title":"Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions","created":"2018-03-27","cited_by_count":6},{"id":"2007.01397","title":"Adaptive Braking for Mitigating Gradient Delay","created":"2020-07-02","cited_by_count":3},{"id":"2010.10687","title":"Is Batch Norm unique? An empirical investigation and prescription to emulate the best properties of common normalizers without batch dependence","created":"2020-10-21","cited_by_count":3},{"id":"2104.09648","title":"Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation","created":"2021-04-19","cited_by_count":3},{"id":"1703.04140","title":"Multiscale Hierarchical Convolutional Networks","created":"2017-03-12","cited_by_count":1}],"next_cursor":null}