{"list":"other","total":102,"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"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":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1707.08819","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","created":"2017-07-27","cited_by_count":377},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"2003.01826","title":"Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions","created":"2020-03-03","cited_by_count":280},{"id":"1904.04971","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","created":"2019-04-10","cited_by_count":273},{"id":"2002.12416","title":"Learning in the Frequency Domain","created":"2020-02-27","cited_by_count":198},{"id":"2103.16562","title":"Boundary IoU: Improving Object-Centric Image Segmentation Evaluation","created":"2021-03-30","cited_by_count":188},{"id":"2012.11879","title":"FcaNet: Frequency Channel Attention Networks","created":"2020-12-22","cited_by_count":179},{"id":"1907.05740","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","created":"2019-07-12","cited_by_count":166},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2002.10120","title":"Semantic Flow for Fast and Accurate Scene Parsing","created":"2020-02-24","cited_by_count":128},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1807.05713","title":"Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models","created":"2018-07-16","cited_by_count":119},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"2210.05844","title":"SegViT: Semantic Segmentation with Plain Vision Transformers","created":"2022-10-12","cited_by_count":106},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81},{"id":"2108.02158","title":"Physics-based Noise Modeling for Extreme Low-light Photography","created":"2021-08-04","cited_by_count":67},{"id":"2008.09604","title":"Delving Deeper into Anti-aliasing in ConvNets","created":"2020-08-21","cited_by_count":60},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59},{"id":"2308.15085","title":"Learning to Upsample by Learning to Sample","created":"2023-08-29","cited_by_count":57},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"2003.08866","title":"Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation","created":"2020-03-19","cited_by_count":51},{"id":"2103.04133","title":"Learning Statistical Texture for Semantic Segmentation","created":"2021-03-06","cited_by_count":51},{"id":"2408.12879","title":"Frequency-aware Feature Fusion for Dense Image Prediction","created":"2024-08-23","cited_by_count":48},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"2104.09805","title":"CTNet: Context-based Tandem Network for Semantic Segmentation","created":"2021-04-20","cited_by_count":43},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41},{"id":"1903.02120","title":"Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation","created":"2019-03-05","cited_by_count":34},{"id":"2403.05369","title":"Frequency-Adaptive Dilated Convolution for Semantic Segmentation","created":"2024-03-08","cited_by_count":34},{"id":"1907.07156","title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","created":"2019-07-16","cited_by_count":33},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32},{"id":"2007.14313","title":"Deep frequency principle towards understanding why deeper learning is faster","created":"2020-07-28","cited_by_count":31},{"id":"2206.08655","title":"Learning Implicit Feature Alignment Function for Semantic Segmentation","created":"2022-06-17","cited_by_count":31},{"id":"2012.03110","title":"Spectral Distribution Aware Image Generation","created":"2020-12-05","cited_by_count":29},{"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":"2204.00491","title":"FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting","created":"2022-04-01","cited_by_count":28},{"id":"2403.07589","title":"PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution","created":"2024-03-12","cited_by_count":28},{"id":"2502.20087","title":"OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels","created":"2025-02-27","cited_by_count":25},{"id":"1807.07466","title":"Guided Upsampling Network for Real-Time Semantic Segmentation","created":"2018-07-19","cited_by_count":24},{"id":"2312.11967","title":"Context Disentangling and Prototype Inheriting for Robust Visual Grounding","created":"2023-12-19","cited_by_count":23},{"id":"2109.11071","title":"Learning to Downsample for Segmentation of Ultra-High Resolution Images","created":"2021-09-22","cited_by_count":19},{"id":"2503.18783","title":"Frequency Dynamic Convolution for Dense Image Prediction","created":"2025-03-24","cited_by_count":19},{"id":"1802.08960","title":"Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs","created":"2018-02-25","cited_by_count":15},{"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":"2303.15390","title":"Learning to Zoom and Unzoom","created":"2023-03-27","cited_by_count":11},{"id":"2403.09065","title":"When Semantic Segmentation Meets Frequency Aliasing","created":"2024-03-14","cited_by_count":10},{"id":"2304.12406","title":"AutoFocusFormer: Image Segmentation off the Grid","created":"2023-04-24","cited_by_count":9},{"id":"1906.06392","title":"Instance Segmentation with Point Supervision","created":"2019-06-14","cited_by_count":8},{"id":"2404.00513","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","created":"2024-03-31","cited_by_count":7}],"next_cursor":"100"}