{"list":"other","total":64,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1905.10650","title":"Are Sixteen Heads Really Better than One?","created":"2019-05-25","cited_by_count":816},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1708.06519","title":"Learning Efficient Convolutional Networks through Network Slimming","created":"2017-08-22","cited_by_count":676},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1902.09574","title":"The State of Sparsity in Deep Neural Networks","created":"2019-02-25","cited_by_count":476},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2007.12223","title":"The Lottery Ticket Hypothesis for Pre-trained BERT Networks","created":"2020-07-23","cited_by_count":275},{"id":"2004.04037","title":"DynaBERT: Dynamic BERT with Adaptive Width and Depth","created":"2020-04-08","cited_by_count":251},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"2002.08307","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","created":"2020-02-19","cited_by_count":185},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2012.15701","title":"BinaryBERT: Pushing the Limit of BERT Quantization","created":"2020-12-31","cited_by_count":178},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162},{"id":"2009.12812","title":"TernaryBERT: Distillation-aware Ultra-low Bit BERT","created":"2020-09-27","cited_by_count":148},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127},{"id":"2002.02925","title":"BERT-of-Theseus: Compressing BERT by Progressive Module Replacing","created":"2020-02-07","cited_by_count":113},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"1711.05852","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","created":"2017-11-15","cited_by_count":101},{"id":"2002.11985","title":"Compressing Large-Scale Transformer-Based Models: A Case Study on BERT","created":"2020-02-27","cited_by_count":96},{"id":"2010.10732","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","created":"2020-10-21","cited_by_count":93},{"id":"2010.13369","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","created":"2020-10-26","cited_by_count":93},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2101.08940","title":"Hessian-Aware Pruning and Optimal Neural Implant","created":"2021-01-22","cited_by_count":45},{"id":"2109.08406","title":"Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers","created":"2021-09-17","cited_by_count":30},{"id":"1909.12486","title":"Reweighted Proximal Pruning for Large-Scale Language Representation","created":"2019-09-27","cited_by_count":29},{"id":"2003.11342","title":"Circumventing Outliers of AutoAugment with Knowledge Distillation","created":"2020-03-25","cited_by_count":29},{"id":"2109.02220","title":"GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization","created":"2021-09-06","cited_by_count":29},{"id":"2005.03403","title":"SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation","created":"2020-05-07","cited_by_count":16},{"id":"1701.08498","title":"Efficient DC Algorithm for Constrained Sparse Optimization","created":"2017-01-30","cited_by_count":5}],"next_cursor":null}