{"list":"other","total":75,"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2001.05566","title":"Image Segmentation Using Deep Learning: A Survey","created":"2020-01-15","cited_by_count":660},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2004.02806","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","created":"2020-04-01","cited_by_count":397},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2106.14156","title":"Post-Training Quantization for Vision Transformer","created":"2021-06-27","cited_by_count":278},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"1909.12326","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","created":"2019-09-26","cited_by_count":222},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207},{"id":"2005.00743","title":"Synthesizer: Rethinking Self-Attention in Transformer Models","created":"2020-05-02","cited_by_count":205},{"id":"2004.03333","title":"Binary Neural Networks: A Survey","created":"2020-03-31","cited_by_count":190},{"id":"2003.03488","title":"ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions","created":"2020-03-07","cited_by_count":184},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"1909.10788","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","created":"2019-09-24","cited_by_count":169},{"id":"2108.07009","title":"Pixel Difference Networks for Efficient Edge Detection","created":"2021-08-16","cited_by_count":168},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"1711.11294","title":"Towards Accurate Binary Convolutional Neural Network","created":"2017-11-30","cited_by_count":149},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"2111.12082","title":"PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer","created":"2021-11-23","cited_by_count":120},{"id":"2003.11535","title":"Training Binary Neural Networks with Real-to-Binary Convolutions","created":"2020-03-25","cited_by_count":112},{"id":"2105.14103","title":"An Attention Free Transformer","created":"2021-05-28","cited_by_count":112},{"id":"1909.13863","title":"XNOR-Net++: Improved Binary Neural Networks","created":"2019-09-30","cited_by_count":97},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79},{"id":"2105.13677","title":"ResT: An Efficient Transformer for Visual Recognition","created":"2021-05-28","cited_by_count":79},{"id":"2203.06390","title":"BiBERT: Accurate Fully Binarized BERT","created":"2022-03-12","cited_by_count":73},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64},{"id":"1904.02823","title":"Regularizing Activation Distribution for Training Binarized Deep Networks","created":"2019-04-04","cited_by_count":61},{"id":"1611.01600","title":"Loss-aware Binarization of Deep Networks","created":"2016-11-05","cited_by_count":56},{"id":"2205.13016","title":"BiT: Robustly Binarized Multi-distilled Transformer","created":"2022-05-25","cited_by_count":52},{"id":"2106.11309","title":"How Do Adam and Training Strategies Help BNNs Optimization?","created":"2021-06-21","cited_by_count":46},{"id":"2107.02823","title":"Deep Learning for Micro-expression Recognition: A Survey","created":"2021-07-06","cited_by_count":43},{"id":"1811.01335","title":"Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance","created":"2018-11-04","cited_by_count":42},{"id":"2111.15127","title":"A Unified Pruning Framework for Vision Transformers","created":"2021-11-30","cited_by_count":40},{"id":"2207.05557","title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","created":"2022-07-12","cited_by_count":40},{"id":"2010.04871","title":"Training Binary Neural Networks through Learning with Noisy Supervision","created":"2020-10-10","cited_by_count":39},{"id":"2103.00841","title":"Learning Frequency Domain Approximation for Binary Neural Networks","created":"2021-03-01","cited_by_count":38},{"id":"2010.07565","title":"Bi-GCN: Binary Graph Convolutional Network","created":"2020-10-15","cited_by_count":28},{"id":"2203.03952","title":"ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer","created":"2022-03-08","cited_by_count":28},{"id":"1808.05240","title":"Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks","created":"2018-08-15","cited_by_count":21},{"id":"1908.06314","title":"Bayesian Optimized 1-Bit CNNs","created":"2019-08-17","cited_by_count":14},{"id":"2110.05185","title":"Dynamic Binary Neural Network by learning channel-wise thresholds","created":"2021-10-08","cited_by_count":13},{"id":"2207.02970","title":"Network Binarization via Contrastive Learning","created":"2022-07-06","cited_by_count":12},{"id":"2205.12635","title":"MoCoViT: Mobile Convolutional Vision Transformer","created":"2022-05-25","cited_by_count":11},{"id":"1901.02662","title":"Deep Semantic Multimodal Hashing Network for Scalable Image-Text and Video-Text Retrievals","created":"2019-01-09","cited_by_count":8}],"next_cursor":null}