{"list":"other","total":56,"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":"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"2012.11879","title":"FcaNet: Frequency Channel Attention Networks","created":"2020-12-22","cited_by_count":179},{"id":"1908.03930","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","created":"2019-08-11","cited_by_count":178},{"id":"1807.06514","title":"BAM: Bottleneck Attention Module","created":"2018-07-17","cited_by_count":172},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"2103.13425","title":"Diverse Branch Block: Building a Convolution as an Inception-like Unit","created":"2021-03-24","cited_by_count":87},{"id":"1808.08127","title":"Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks","created":"2018-08-23","cited_by_count":76},{"id":"1811.12006","title":"Global Second-order Pooling Convolutional Networks","created":"2018-11-29","cited_by_count":66},{"id":"1903.10829","title":"SRM : A Style-based Recalibration Module for Convolutional Neural Networks","created":"2019-03-26","cited_by_count":66},{"id":"1904.05873","title":"An Empirical Study of Spatial Attention Mechanisms in Deep Networks","created":"2019-04-11","cited_by_count":58},{"id":"1811.10495","title":"ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks","created":"2018-11-26","cited_by_count":53},{"id":"2105.01883","title":"RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition","created":"2021-05-05","cited_by_count":40},{"id":"1905.10671","title":"DIANet: Dense-and-Implicit Attention Network","created":"2019-05-25","cited_by_count":37},{"id":"1905.09646","title":"Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks","created":"2019-05-23","cited_by_count":33},{"id":"2004.11627","title":"Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning","created":"2020-04-24","cited_by_count":30},{"id":"1908.04008","title":"Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise","created":"2019-08-12","cited_by_count":28},{"id":"2006.12030","title":"DO-Conv: Depthwise Over-parameterized Convolutional Layer","created":"2020-06-22","cited_by_count":28},{"id":"2206.13951","title":"Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment","created":"2022-06-28","cited_by_count":27},{"id":"2205.05671","title":"RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization","created":"2022-05-11","cited_by_count":19},{"id":"2107.05033","title":"Blending Pruning Criteria for Convolutional Neural Networks","created":"2021-07-11","cited_by_count":13},{"id":"2109.03508","title":"RepNAS: Searching for Efficient Re-parameterizing Blocks","created":"2021-09-08","cited_by_count":11},{"id":"2203.12868","title":"DyRep: Bootstrapping Training with Dynamic Re-parameterization","created":"2022-03-24","cited_by_count":11},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7},{"id":"1912.04749","title":"Efficient Differentiable Neural Architecture Search with Meta Kernels","created":"2019-12-10","cited_by_count":6},{"id":"1911.10305","title":"Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families","created":"2019-11-23","cited_by_count":5},{"id":"2302.10184","title":"AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios","created":"2023-02-05","cited_by_count":4},{"id":"2208.10322","title":"Mix-Pooling Strategy for Attention Mechanism","created":"2022-08-22","cited_by_count":3},{"id":"2110.13465","title":"CS-Rep: Making Speaker Verification Networks Embracing Re-parameterization","created":"2021-10-26","cited_by_count":2},{"id":"2205.14477","title":"MDMLP: Image Classification from Scratch on Small Datasets with MLP","created":"2022-05-28","cited_by_count":2}],"next_cursor":null}