{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"1906.10771","title":"Importance Estimation for Neural Network Pruning","created":"2019-06-25","cited_by_count":541},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1602.01528","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","created":"2016-02-04","cited_by_count":295},{"id":"2002.10179","title":"HRank: Filter Pruning using High-Rank Feature Map","created":"2020-02-24","cited_by_count":292},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1711.08393","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","created":"2017-11-22","cited_by_count":189},{"id":"1810.11809","title":"Discrimination-aware Channel Pruning for Deep Neural Networks","created":"2018-10-28","cited_by_count":171},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1911.07412","title":"Provable Filter Pruning for Efficient Neural Networks","created":"2019-11-18","cited_by_count":98},{"id":"2010.10732","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","created":"2020-10-21","cited_by_count":93},{"id":"2110.13981","title":"CHIP: CHannel Independence-based Pruning for Compact Neural Networks","created":"2021-10-26","cited_by_count":78},{"id":"2006.14389","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","created":"2020-06-24","cited_by_count":76},{"id":"1904.12368","title":"Towards Efficient Model Compression via Learned Global Ranking","created":"2019-04-28","cited_by_count":75},{"id":"2007.03938","title":"Operation-Aware Soft Channel Pruning using Differentiable Masks","created":"2020-07-08","cited_by_count":74},{"id":"2003.01794","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","created":"2020-03-03","cited_by_count":70},{"id":"1703.08651","title":"More is Less: A More Complicated Network with Less Inference Complexity","created":"2017-03-25","cited_by_count":66},{"id":"2205.05676","title":"Revisiting Random Channel Pruning for Neural Network Compression","created":"2022-05-11","cited_by_count":50},{"id":"2010.14819","title":"Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets","created":"2020-10-28","cited_by_count":49},{"id":"2103.06877","title":"Fast and Accurate Model Scaling","created":"2021-03-11","cited_by_count":46},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41},{"id":"2105.11228","title":"Towards Compact CNNs via Collaborative Compression","created":"2021-05-24","cited_by_count":36},{"id":"1709.06030","title":"N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning","created":"2017-09-18","cited_by_count":33},{"id":"2007.05078","title":"A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces","created":"2020-07-09","cited_by_count":32},{"id":"2102.03214","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","created":"2021-02-05","cited_by_count":30},{"id":"2010.12870","title":"Efficient Learning in Non-Stationary Linear Markov Decision Processes","created":"2020-10-24","cited_by_count":26},{"id":"2111.04613","title":"Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems","created":"2021-11-08","cited_by_count":26},{"id":"1801.07365","title":"Learning to Prune Filters in Convolutional Neural Networks","created":"2018-01-23","cited_by_count":25},{"id":"2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","created":"2021-10-15","cited_by_count":24},{"id":"2106.12112","title":"Bregman Gradient Policy Optimization","created":"2021-06-23","cited_by_count":17},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11},{"id":"2307.08483","title":"Differentiable Transportation Pruning","created":"2023-07-17","cited_by_count":10},{"id":"2312.14776","title":"Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold","created":"2023-12-22","cited_by_count":3}],"next_cursor":null}