{"list":"other","total":54,"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":"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"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":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"1911.11907","title":"GhostNet: More Features from Cheap Operations","created":"2019-11-27","cited_by_count":410},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"1910.01348","title":"On the Efficacy of Knowledge Distillation","created":"2019-10-03","cited_by_count":381},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"1711.11503","title":"Convolutional Networks with Adaptive Inference Graphs","created":"2017-11-30","cited_by_count":148},{"id":"2003.07326","title":"Resolution Adaptive Networks for Efficient Inference","created":"2020-03-16","cited_by_count":146},{"id":"1612.02297","title":"Spatially Adaptive Computation Time for Residual Networks","created":"2016-12-07","cited_by_count":118},{"id":"2012.09243","title":"Neural Pruning via Growing Regularization","created":"2020-12-16","cited_by_count":97},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83},{"id":"2003.10401","title":"Learning Dynamic Routing for Semantic Segmentation","created":"2020-03-23","cited_by_count":79},{"id":"1710.04773","title":"Residual Connections Encourage Iterative Inference","created":"2017-10-13","cited_by_count":77},{"id":"2303.04935","title":"X-Pruner: eXplainable Pruning for Vision Transformers","created":"2023-03-08","cited_by_count":68},{"id":"1908.06294","title":"Improved Techniques for Training Adaptive Deep Networks","created":"2019-08-17","cited_by_count":66},{"id":"1612.07771","title":"Highway and Residual Networks learn Unrolled Iterative Estimation","created":"2016-12-22","cited_by_count":52},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36},{"id":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31},{"id":"2212.04884","title":"Co-training $2^L$ Submodels for Visual Recognition","created":"2022-12-09","cited_by_count":8},{"id":"2008.06635","title":"Orthogonalized SGD and Nested Architectures for Anytime Neural Networks","created":"2020-08-15","cited_by_count":5}],"next_cursor":null}