{"list":"other","total":61,"rows":[{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"2107.00645","title":"Global Filter Networks for Image Classification","created":"2021-07-01","cited_by_count":260},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248},{"id":"2103.10158","title":"TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation","created":"2021-03-18","cited_by_count":227},{"id":"1611.05594","title":"SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning","created":"2016-11-17","cited_by_count":219},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201},{"id":"1805.07071","title":"Multi-level Wavelet-CNN for Image Restoration","created":"2018-05-18","cited_by_count":184},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"1712.07628","title":"Improving Generalization Performance by Switching from Adam to SGD","created":"2017-12-20","cited_by_count":125},{"id":"1810.13243","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","created":"2018-10-29","cited_by_count":110},{"id":"2005.03337","title":"Wavelet Integrated CNNs for Noise-Robust Image Classification","created":"2020-05-07","cited_by_count":60},{"id":"1907.12904","title":"Learned Image Downscaling for Upscaling using Content Adaptive Resampler","created":"2019-07-22","cited_by_count":55},{"id":"2006.12230","title":"HookNet: multi-resolution convolutional neural networks for semantic segmentation in histopathology whole-slide images","created":"2020-06-22","cited_by_count":45},{"id":"1904.06836","title":"Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization","created":"2019-04-15","cited_by_count":42},{"id":"2007.03347","title":"SpinalNet: Deep Neural Network with Gradual Input","created":"2020-07-07","cited_by_count":40},{"id":"2008.10400","title":"An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit Recognition","created":"2020-08-12","cited_by_count":30},{"id":"1807.03848","title":"Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition","created":"2018-07-10","cited_by_count":22},{"id":"2004.13824","title":"Pyramid Attention Networks for Image Restoration","created":"2020-04-28","cited_by_count":17},{"id":"1912.05035","title":"Deep Adaptive Wavelet Network","created":"2019-12-10","cited_by_count":16},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16},{"id":"1803.02758","title":"RTSeg: Real-time Semantic Segmentation Comparative Study","created":"2018-03-07","cited_by_count":11},{"id":"2005.14461","title":"WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation","created":"2020-05-29","cited_by_count":10},{"id":"1809.02209","title":"ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions","created":"2018-09-06","cited_by_count":5},{"id":"2201.10271","title":"Convolutional Xformers for Vision","created":"2022-01-25","cited_by_count":5},{"id":"2101.02268","title":"LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification","created":"2021-01-06","cited_by_count":4},{"id":"2205.01777","title":"Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation","created":"2022-05-03","cited_by_count":2}],"next_cursor":null}