{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2104.00298","title":"EfficientNetV2: Smaller Models and Faster Training","created":"2021-04-01","cited_by_count":1135},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1811.11721","title":"CCNet: Criss-Cross Attention for Semantic Segmentation","created":"2018-11-28","cited_by_count":718},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1905.02716","title":"EDVR: Video Restoration with Enhanced Deformable Convolutional Networks","created":"2019-05-07","cited_by_count":494},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1907.08610","title":"Lookahead Optimizer: k steps forward, 1 step back","created":"2019-07-19","cited_by_count":336},{"id":"1807.03247","title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","created":"2018-07-09","cited_by_count":307},{"id":"2010.07468","title":"AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradients","created":"2020-10-15","cited_by_count":283},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"1910.05895","title":"Transformers without Tears: Improving the Normalization of Self-Attention","created":"2019-10-14","cited_by_count":153},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"1810.11579","title":"$A^2$-Nets: Double Attention Networks","created":"2018-10-27","cited_by_count":136},{"id":"1812.11941","title":"High Quality Monocular Depth Estimation via Transfer Learning","created":"2018-12-31","cited_by_count":133},{"id":"1811.12814","title":"Graph-Based Global Reasoning Networks","created":"2018-11-30","cited_by_count":120},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107},{"id":"2105.14021","title":"Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging","created":"2021-05-28","cited_by_count":104},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2004.01461","title":"Gradient Centralization: A New Optimization Technique for Deep Neural Networks","created":"2020-04-03","cited_by_count":82},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"2003.09229","title":"Learning to Encode Position for Transformer with Continuous Dynamical Model","created":"2020-03-13","cited_by_count":61},{"id":"2009.06613","title":"High-Resolution Deep Image Matting","created":"2020-09-14","cited_by_count":36},{"id":"1910.04209","title":"On the adequacy of untuned warmup for adaptive optimization","created":"2019-10-09","cited_by_count":35},{"id":"1910.12060","title":"MAP-Net: Multi Attending Path Neural Network for Building Footprint Extraction from Remote Sensed Imagery","created":"2019-10-26","cited_by_count":35},{"id":"2012.13375","title":"Global Context Networks","created":"2020-12-24","cited_by_count":35},{"id":"2010.13382","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","created":"2020-10-26","cited_by_count":28},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28},{"id":"2106.13731","title":"Ranger21: a synergistic deep learning optimizer","created":"2021-06-25","cited_by_count":22},{"id":"1902.07474","title":"Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks","created":"2019-02-20","cited_by_count":7},{"id":"1911.10581","title":"Pixel Adaptive Filtering Units","created":"2019-11-24","cited_by_count":2}],"next_cursor":null}