{"list":"other","total":96,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"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":"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":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"1612.02295","title":"Large-Margin Softmax Loss for Convolutional Neural Networks","created":"2016-12-07","cited_by_count":296},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"1901.02985","title":"Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation","created":"2019-01-10","cited_by_count":260},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"1404.4661","title":"Learning Fine-grained Image Similarity with Deep Ranking","created":"2014-04-17","cited_by_count":190},{"id":"2008.08290","title":"Attribute Prototype Network for Zero-Shot Learning","created":"2020-08-19","cited_by_count":160},{"id":"1805.10180","title":"Pyramid Attention Network for Semantic Segmentation","created":"2018-05-25","cited_by_count":149},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1907.13426","title":"Expectation-Maximization Attention Networks for Semantic Segmentation","created":"2019-07-31","cited_by_count":147},{"id":"2007.01947","title":"Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation","created":"2020-07-03","cited_by_count":144},{"id":"1803.06815","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","created":"2018-03-19","cited_by_count":133},{"id":"1805.03438","title":"Robust Classification with Convolutional Prototype Learning","created":"2018-05-09","cited_by_count":123},{"id":"2004.01547","title":"Context Prior for Scene Segmentation","created":"2020-04-03","cited_by_count":121},{"id":"1804.09337","title":"Learning a Discriminative Feature Network for Semantic Segmentation","created":"2018-04-25","cited_by_count":114},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"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":"1910.06962","title":"SegSort: Segmentation by Discriminative Sorting of Segments","created":"2019-10-15","cited_by_count":96},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"1901.10514","title":"Hyperspherical Prototype Networks","created":"2019-01-29","cited_by_count":86},{"id":"1912.03330","title":"ClusterFit: Improving Generalization of Visual Representations","created":"2019-12-06","cited_by_count":82},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"1912.10917","title":"FasterSeg: Searching for Faster Real-time Semantic Segmentation","created":"2019-12-23","cited_by_count":73},{"id":"2003.05128","title":"Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks","created":"2020-03-11","cited_by_count":70},{"id":"2106.00131","title":"Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation","created":"2021-05-31","cited_by_count":65},{"id":"1909.02651","title":"Semantic Correlation Promoted Shape-Variant Context for Segmentation","created":"2019-09-05","cited_by_count":61},{"id":"1712.08273","title":"Recurrent Pixel Embedding for Instance Grouping","created":"2017-12-22","cited_by_count":58},{"id":"1808.04699","title":"Improving Generalization via Scalable Neighborhood Component Analysis","created":"2018-08-14","cited_by_count":53},{"id":"1911.01664","title":"Adaptive Context Network for Scene Parsing","created":"2019-11-05","cited_by_count":51},{"id":"2004.07684","title":"Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts","created":"2020-04-16","cited_by_count":51},{"id":"1803.10335","title":"Adaptive Affinity Fields for Semantic Segmentation","created":"2018-03-27","cited_by_count":48},{"id":"2108.11819","title":"Mining Contextual Information Beyond Image for Semantic Segmentation","created":"2021-08-26","cited_by_count":48},{"id":"2003.10211","title":"Spatial Pyramid Based Graph Reasoning for Semantic Segmentation","created":"2020-03-23","cited_by_count":47},{"id":"1511.03328","title":"Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform","created":"2015-11-10","cited_by_count":46},{"id":"2007.09690","title":"Class-wise Dynamic Graph Convolution for Semantic Segmentation","created":"2020-07-19","cited_by_count":44},{"id":"1608.08792","title":"CliqueCNN: Deep Unsupervised Exemplar Learning","created":"2016-08-31","cited_by_count":41},{"id":"2108.12382","title":"ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation","created":"2021-08-27","cited_by_count":40},{"id":"1810.10804","title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","created":"2018-10-25","cited_by_count":39},{"id":"1511.02674","title":"Semantic Segmentation with Boundary Neural Fields","created":"2015-11-09","cited_by_count":37},{"id":"1708.04607","title":"Segmentation-Aware Convolutional Networks Using Local Attention Masks","created":"2017-08-15","cited_by_count":31},{"id":"1606.07230","title":"Deep Learning Markov Random Field for Semantic Segmentation","created":"2016-06-23","cited_by_count":27},{"id":"1512.01192","title":"Prototypical Priors: From Improving Classification to Zero-Shot Learning","created":"2015-12-03","cited_by_count":14},{"id":"2012.07489","title":"Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU","created":"2020-12-14","cited_by_count":8},{"id":"2108.01866","title":"Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation","created":"2021-08-04","cited_by_count":7}],"next_cursor":null}