{"list":"other","total":54,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1707.06342","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","created":"2017-07-20","cited_by_count":442},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1707.04780","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","created":"2017-07-15","cited_by_count":328},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1701.05369","title":"Variational Dropout Sparsifies Deep Neural Networks","created":"2017-01-19","cited_by_count":265},{"id":"1608.04493","title":"Dynamic Network Surgery for Efficient DNNs","created":"2016-08-16","cited_by_count":233},{"id":"1711.05908","title":"NISP: Pruning Networks using Neuron Importance Score Propagation","created":"2017-11-16","cited_by_count":228},{"id":"1607.03250","title":"Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures","created":"2016-07-12","cited_by_count":221},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"1902.05967","title":"Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization","created":"2019-02-15","cited_by_count":189},{"id":"1909.11957","title":"Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks","created":"2019-09-26","cited_by_count":160},{"id":"1711.05136","title":"Deep Rewiring: Training very sparse deep networks","created":"2017-11-14","cited_by_count":139},{"id":"2102.02887","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","created":"2021-02-04","cited_by_count":110},{"id":"2010.13369","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","created":"2020-10-26","cited_by_count":93},{"id":"1911.03090","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","created":"2019-11-08","cited_by_count":89},{"id":"1910.03723","title":"Knowledge Distillation from Internal Representations","created":"2019-10-08","cited_by_count":87},{"id":"1905.09717","title":"Network Pruning via Transformable Architecture Search","created":"2019-05-23","cited_by_count":80},{"id":"2110.14032","title":"MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge","created":"2021-10-26","cited_by_count":79},{"id":"2001.00138","title":"PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning","created":"2020-01-01","cited_by_count":76},{"id":"1802.10399","title":"Compressing Neural Networks using the Variational Information Bottleneck","created":"2018-02-28","cited_by_count":59},{"id":"1706.04983","title":"FreezeOut: Accelerate Training by Progressively Freezing Layers","created":"2017-06-15","cited_by_count":54},{"id":"1909.05073","title":"PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices","created":"2019-09-06","cited_by_count":50},{"id":"2010.12562","title":"On the Transformer Growth for Progressive BERT Training","created":"2020-10-23","cited_by_count":49},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48},{"id":"1901.09290","title":"PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration","created":"2019-01-26","cited_by_count":41},{"id":"1705.07283","title":"Structured Bayesian Pruning via Log-Normal Multiplicative Noise","created":"2017-05-20","cited_by_count":39},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37},{"id":"1907.02124","title":"Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?","created":"2019-07-03","cited_by_count":32},{"id":"2102.03161","title":"PipeTransformer: Automated Elastic Pipelining for Distributed Training of Transformers","created":"2021-02-05","cited_by_count":23},{"id":"2102.11068","title":"Lottery Ticket Preserves Weight Correlation: Is It Desirable or Not?","created":"2021-02-19","cited_by_count":22},{"id":"2201.06227","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","created":"2022-01-17","cited_by_count":22},{"id":"1702.08635","title":"Learning What Data to Learn","created":"2017-02-28","cited_by_count":21},{"id":"2002.11474","title":"RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition","created":"2020-02-19","cited_by_count":19},{"id":"2007.00389","title":"Single Shot Structured Pruning Before Training","created":"2020-07-01","cited_by_count":19},{"id":"2001.07710","title":"An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices","created":"2020-01-20","cited_by_count":18},{"id":"2012.15045","title":"Reservoir Transformers","created":"2020-12-30","cited_by_count":18},{"id":"2011.14087","title":"FreezeNet: Full Performance by Reduced Storage Costs","created":"2020-11-28","cited_by_count":13},{"id":"2108.11033","title":"GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity","created":"2021-08-25","cited_by_count":10},{"id":"2012.02792","title":"Weight Update Skipping: Reducing Training Time for Artificial Neural Networks","created":"2020-12-05","cited_by_count":6},{"id":"1803.05909","title":"Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning","created":"2018-03-15","cited_by_count":4},{"id":"2010.08038","title":"Why Layer-Wise Learning is Hard to Scale-up and a Possible Solution via Accelerated Downsampling","created":"2020-10-15","cited_by_count":3}],"next_cursor":null}