{"list":"other","total":73,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"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":"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":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"id":"1905.13545","title":"High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks","created":"2019-05-28","cited_by_count":310},{"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":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248},{"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":"1905.02188","title":"CARAFE: Content-Aware ReAssembly of FEatures","created":"2019-05-06","cited_by_count":119},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1908.00672","title":"Indices Matter: Learning to Index for Deep Image Matting","created":"2019-08-02","cited_by_count":93},{"id":"2108.07058","title":"FaPN: Feature-aligned Pyramid Network for Dense Image Prediction","created":"2021-08-16","cited_by_count":81},{"id":"2203.05151","title":"Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity","created":"2022-03-10","cited_by_count":77},{"id":"1611.08323","title":"Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes","created":"2016-11-24","cited_by_count":71},{"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":"2308.15085","title":"Learning to Upsample by Learning to Sample","created":"2023-08-29","cited_by_count":57},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2203.15674","title":"Exploring Frequency Adversarial Attacks for Face Forgery Detection","created":"2022-03-29","cited_by_count":45},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45},{"id":"1804.03821","title":"ExFuse: Enhancing Feature Fusion for Semantic Segmentation","created":"2018-04-11","cited_by_count":42},{"id":"2012.02124","title":"Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline","created":"2020-12-03","cited_by_count":42},{"id":"2011.14288","title":"Learning Affinity-Aware Upsampling for Deep Image Matting","created":"2020-11-29","cited_by_count":37},{"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":"1512.06735","title":"Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs","created":"2015-12-21","cited_by_count":32},{"id":"2209.12866","title":"SAPA: Similarity-Aware Point Affiliation for Feature Upsampling","created":"2022-09-26","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":"2204.00491","title":"FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting","created":"2022-04-01","cited_by_count":28},{"id":"2207.10392","title":"FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling","created":"2022-07-21","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":"2012.04733","title":"CARAFE++: Unified Content-Aware ReAssembly of FEatures","created":"2020-12-07","cited_by_count":20},{"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":"2302.06298","title":"Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance","created":"2023-02-13","cited_by_count":13},{"id":"2102.13002","title":"Maximizing Cosine Similarity Between Spatial Features for Unsupervised Domain Adaptation in Semantic Segmentation","created":"2021-02-25","cited_by_count":12},{"id":"2303.01906","title":"Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning","created":"2023-03-03","cited_by_count":11},{"id":"2207.04415","title":"SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow","created":"2022-07-10","cited_by_count":10},{"id":"2403.09065","title":"When Semantic Segmentation Meets Frequency Aliasing","created":"2024-03-14","cited_by_count":10},{"id":"2404.00513","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","created":"2024-03-31","cited_by_count":7},{"id":"2301.04870","title":"Semantic Segmentation via Pixel-to-Center Similarity Calculation","created":"2023-01-12","cited_by_count":3},{"id":"2308.06548","title":"Revisiting Vision Transformer from the View of Path Ensemble","created":"2023-08-12","cited_by_count":3}],"next_cursor":null}