{"list":"other","total":68,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1902.07830","title":"Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges","created":"2019-02-21","cited_by_count":314},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"2004.02147","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","created":"2020-04-05","cited_by_count":294},{"id":"1906.08988","title":"A Fourier Perspective on Model Robustness in Computer Vision","created":"2019-06-21","cited_by_count":288},{"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":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2002.10120","title":"Semantic Flow for Fast and Accurate Scene Parsing","created":"2020-02-24","cited_by_count":128},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127},{"id":"1904.05373","title":"Pixel-Adaptive Convolutional Neural Networks","created":"2019-04-10","cited_by_count":126},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103},{"id":"1903.08469","title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","created":"2019-03-20","cited_by_count":100},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2101.06085","title":"Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes","created":"2021-01-15","cited_by_count":89},{"id":"2206.02066","title":"PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers","created":"2022-06-04","cited_by_count":84},{"id":"1803.01207","title":"Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learning","created":"2018-03-03","cited_by_count":81},{"id":"2012.11582","title":"HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation","created":"2020-12-21","cited_by_count":66},{"id":"2110.08059","title":"FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes","created":"2021-10-15","cited_by_count":66},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62},{"id":"2008.09604","title":"Delving Deeper into Anti-aliasing in ConvNets","created":"2020-08-21","cited_by_count":60},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"2203.12198","title":"Deep Frequency Filtering for Domain Generalization","created":"2022-03-23","cited_by_count":43},{"id":"1903.03777","title":"Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search","created":"2019-03-09","cited_by_count":39},{"id":"2204.02681","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","created":"2022-04-06","cited_by_count":33},{"id":"2107.13335","title":"WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification","created":"2021-07-28","cited_by_count":29},{"id":"2106.04067","title":"LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation","created":"2021-06-08","cited_by_count":28},{"id":"2309.13190","title":"Spatial-frequency channels, shape bias, and adversarial robustness","created":"2023-09-22","cited_by_count":28},{"id":"2108.03489","title":"Impact of Aliasing on Generalization in Deep Convolutional Networks","created":"2021-08-07","cited_by_count":25},{"id":"2011.11844","title":"Densely connected multidilated convolutional networks for dense prediction tasks","created":"2020-11-21","cited_by_count":21},{"id":"2012.05703","title":"TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems","created":"2020-11-18","cited_by_count":20},{"id":"2112.03740","title":"Dilated convolution with learnable spacings","created":"2021-12-07","cited_by_count":20},{"id":"1808.08931","title":"Smoothed Dilated Convolutions for Improved Dense Prediction","created":"2018-08-27","cited_by_count":19},{"id":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16},{"id":"2011.00993","title":"Real-time Semantic Segmentation with Context Aggregation Network","created":"2020-11-02","cited_by_count":14},{"id":"2308.11568","title":"SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation","created":"2023-08-22","cited_by_count":14},{"id":"2110.00899","title":"Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function","created":"2021-10-03","cited_by_count":11},{"id":"2210.09020","title":"Defects of Convolutional Decoder Networks in Frequency Representation","created":"2022-10-17","cited_by_count":10},{"id":"2310.14221","title":"The Importance of Anti-Aliasing in Tiny Object Detection","created":"2023-10-22","cited_by_count":2}],"next_cursor":null}