{"list":"other","total":52,"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"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":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1812.03443","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","created":"2018-12-09","cited_by_count":485},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"1904.00420","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","created":"2019-03-31","cited_by_count":414},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"id":"1906.01787","title":"Learning Deep Transformer Models for Machine Translation","created":"2019-06-05","cited_by_count":309},{"id":"1901.10430","title":"Pay Less Attention with Lightweight and Dynamic Convolutions","created":"2019-01-29","cited_by_count":211},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188},{"id":"1901.11117","title":"The Evolved Transformer","created":"2019-01-30","cited_by_count":180},{"id":"2004.05565","title":"FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions","created":"2020-04-12","cited_by_count":152},{"id":"1805.11046","title":"Scalable Methods for 8-bit Training of Neural Networks","created":"2018-05-25","cited_by_count":142},{"id":"2005.14187","title":"HAT: Hardware-Aware Transformers for Efficient Natural Language Processing","created":"2020-05-28","cited_by_count":136},{"id":"1907.01845","title":"FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search","created":"2019-07-03","cited_by_count":130},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","cited_by_count":127},{"id":"1804.09849","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","created":"2018-04-26","cited_by_count":102},{"id":"1711.08141","title":"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions","created":"2017-11-22","cited_by_count":93},{"id":"1912.13200","title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","created":"2019-12-31","cited_by_count":82},{"id":"1911.13053","title":"Blockwisely Supervised Neural Architecture Search with Knowledge Distillation","created":"2019-11-29","cited_by_count":81},{"id":"2003.11236","title":"GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet","created":"2020-03-25","cited_by_count":69},{"id":"2103.12424","title":"BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search","created":"2021-03-23","cited_by_count":63},{"id":"1905.13298","title":"DeepShift: Towards Multiplication-Less Neural Networks","created":"2019-05-30","cited_by_count":54},{"id":"2107.02960","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","created":"2021-07-07","cited_by_count":53},{"id":"2010.12785","title":"ShiftAddNet: A Hardware-Inspired Deep Network","created":"2020-10-24","cited_by_count":52},{"id":"2008.01475","title":"Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap","created":"2020-08-04","cited_by_count":50},{"id":"2106.06560","title":"HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers","created":"2021-06-11","cited_by_count":39},{"id":"1608.06049","title":"Local Binary Convolutional Neural Networks","created":"2016-08-22","cited_by_count":38},{"id":"2009.08891","title":"AdderSR: Towards Energy Efficient Image Super-Resolution","created":"2020-09-18","cited_by_count":32},{"id":"2106.13700","title":"ViTAS: Vision Transformer Architecture Search","created":"2021-06-25","cited_by_count":31},{"id":"1910.02543","title":"Improving One-shot NAS by Suppressing the Posterior Fading","created":"2019-10-06","cited_by_count":28},{"id":"2101.11342","title":"Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search","created":"2021-01-27","cited_by_count":27},{"id":"2009.13044","title":"Kernel Based Progressive Distillation for Adder Neural Networks","created":"2020-09-28","cited_by_count":19},{"id":"2101.10015","title":"AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence","created":"2021-01-25","cited_by_count":10}],"next_cursor":null}