{"list":"other","total":56,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"2001.06826","title":"Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement","created":"2020-01-19","cited_by_count":542},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1906.06972","title":"EnlightenGAN: Deep Light Enhancement without Paired Supervision","created":"2019-06-17","cited_by_count":466},{"id":"1805.01934","title":"Learning to See in the Dark","created":"2018-05-04","cited_by_count":460},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1904.11486","title":"Making Convolutional Networks Shift-Invariant Again","created":"2019-04-25","cited_by_count":391},{"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":"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":"1906.03525","title":"Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentation","created":"2019-06-08","cited_by_count":142},{"id":"2003.12751","title":"A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising","created":"2020-03-28","cited_by_count":138},{"id":"2002.10120","title":"Semantic Flow for Fast and Accurate Scene Parsing","created":"2020-02-24","cited_by_count":128},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103},{"id":"2007.10035","title":"Improving Semantic Segmentation via Decoupled Body and Edge Supervision","created":"2020-07-20","cited_by_count":99},{"id":"2007.04269","title":"SegFix: Model-Agnostic Boundary Refinement for Segmentation","created":"2020-07-08","cited_by_count":97},{"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":"2209.15001","title":"Dilated Neighborhood Attention Transformer","created":"2022-09-29","cited_by_count":64},{"id":"2008.09604","title":"Delving Deeper into Anti-aliasing in ConvNets","created":"2020-08-21","cited_by_count":60},{"id":"1704.01344","title":"Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade","created":"2017-04-05","cited_by_count":53},{"id":"2103.04133","title":"Learning Statistical Texture for Semantic Segmentation","created":"2021-03-06","cited_by_count":51},{"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":"2007.14313","title":"Deep frequency principle towards understanding why deeper learning is faster","created":"2020-07-28","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":"1807.07466","title":"Guided Upsampling Network for Real-Time Semantic Segmentation","created":"2018-07-19","cited_by_count":24},{"id":"2301.04648","title":"Head-Free Lightweight Semantic Segmentation with Linear Transformer","created":"2023-01-11","cited_by_count":22},{"id":"2204.05538","title":"NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night","created":"2022-04-12","cited_by_count":21},{"id":"2110.15156","title":"Blending Anti-Aliasing into Vision Transformer","created":"2021-10-28","cited_by_count":16},{"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":"2204.01716","title":"Estimating Fine-Grained Noise Model via Contrastive Learning","created":"2022-04-03","cited_by_count":14},{"id":"1906.11437","title":"Hard Pixel Mining for Depth Privileged Semantic Segmentation","created":"2019-06-27","cited_by_count":13},{"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":"2104.07216","title":"Learning structure-aware semantic segmentation with image-level supervision","created":"2021-04-15","cited_by_count":4}],"next_cursor":null}