{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"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":"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":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1902.03393","title":"Improved Knowledge Distillation via Teacher Assistant","created":"2019-02-09","cited_by_count":573},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"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":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"1802.04977","title":"Paraphrasing Complex Network: Network Compression via Factor Transfer","created":"2018-02-14","cited_by_count":260},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"1902.04502","title":"Fast-SCNN: Fast Semantic Segmentation Network","created":"2019-02-12","cited_by_count":125},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121},{"id":"2003.13328","title":"Strip Pooling: Rethinking Spatial Pooling for Scene Parsing","created":"2020-03-30","cited_by_count":114},{"id":"2211.16231","title":"Curriculum Temperature for Knowledge Distillation","created":"2022-11-29","cited_by_count":112},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"2007.10035","title":"Improving Semantic Segmentation via Decoupled Body and Edge Supervision","created":"2020-07-20","cited_by_count":99},{"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":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"1908.06955","title":"Dynamic Graph Message Passing Networks","created":"2019-08-19","cited_by_count":62},{"id":"2108.02092","title":"Online Knowledge Distillation for Efficient Pose Estimation","created":"2021-08-04","cited_by_count":55},{"id":"1907.12273","title":"Interlaced Sparse Self-Attention for Semantic Segmentation","created":"2019-07-29","cited_by_count":53},{"id":"2003.00872","title":"AlignSeg: Feature-Aligned Segmentation Networks","created":"2020-02-24","cited_by_count":53},{"id":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38},{"id":"2109.04454","title":"ConvMLP: Hierarchical Convolutional MLPs for Vision","created":"2021-09-09","cited_by_count":37},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24},{"id":"2202.13393","title":"TransKD: Transformer Knowledge Distillation for Efficient Semantic Segmentation","created":"2022-02-27","cited_by_count":17},{"id":"2011.03308","title":"Towards Efficient Scene Understanding via Squeeze Reasoning","created":"2020-11-06","cited_by_count":10},{"id":"2007.08442","title":"Kronecker Attention Networks","created":"2020-07-16","cited_by_count":9},{"id":"2107.13154","title":"Global Aggregation then Local Distribution for Scene Parsing","created":"2021-07-28","cited_by_count":8}],"next_cursor":null}