{"list":"other","total":64,"rows":[{"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"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":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"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":"2003.13678","title":"Designing Network Design Spaces","created":"2020-03-30","cited_by_count":960},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2106.10270","title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","created":"2021-06-18","cited_by_count":569},{"id":"1812.00564","title":"Split learning for health: Distributed deep learning without sharing raw patient data","created":"2018-12-03","cited_by_count":395},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"id":"1810.06060","title":"Distributed learning of deep neural network over multiple agents","created":"2018-10-14","cited_by_count":279},{"id":"2011.03029","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","created":"2020-11-05","cited_by_count":276},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"1608.05148","title":"Full Resolution Image Compression with Recurrent Neural Networks","created":"2016-08-18","cited_by_count":175},{"id":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"id":"1511.06281","title":"Density Modeling of Images using a Generalized Normalization Transformation","created":"2015-11-19","cited_by_count":127},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"1908.05717","title":"Video Compression With Rate-Distortion Autoencoders","created":"2019-08-14","cited_by_count":97},{"id":"1910.14315","title":"BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems","created":"2019-10-31","cited_by_count":95},{"id":"1703.10114","title":"Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks","created":"2017-03-29","cited_by_count":92},{"id":"2006.04240","title":"Improving Inference for Neural Image Compression","created":"2020-06-07","cited_by_count":83},{"id":"1801.08618","title":"JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services","created":"2018-01-25","cited_by_count":80},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79},{"id":"1902.01000","title":"BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services","created":"2019-02-04","cited_by_count":68},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2007.11797","title":"End-to-end Learning of Compressible Features","created":"2020-07-23","cited_by_count":43},{"id":"2108.11898","title":"Supervised Compression for Resource-Constrained Edge Computing Systems","created":"2021-08-21","cited_by_count":31},{"id":"2108.13041","title":"Auto-Split: A General Framework of Collaborative Edge-Cloud AI","created":"2021-08-30","cited_by_count":30},{"id":"2203.04963","title":"Neural Data-Dependent Transform for Learned Image Compression","created":"2022-03-09","cited_by_count":30},{"id":"2007.15818","title":"Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks","created":"2020-07-31","cited_by_count":28},{"id":"2201.02693","title":"BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing","created":"2022-01-07","cited_by_count":28},{"id":"1804.09869","title":"Learning for Video Compression","created":"2018-04-26","cited_by_count":26},{"id":"2102.02913","title":"Progressive Neural Image Compression with Nested Quantization and Latent Ordering","created":"2021-02-04","cited_by_count":24},{"id":"1810.02845","title":"Deep Generative Video Compression","created":"2018-10-05","cited_by_count":23},{"id":"2111.11632","title":"Lossless Compression with Probabilistic Circuits","created":"2021-11-23","cited_by_count":20},{"id":"2011.12913","title":"torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation","created":"2020-11-25","cited_by_count":19},{"id":"2009.12430","title":"Pareto-Optimal Bit Allocation for Collaborative Intelligence","created":"2020-09-25","cited_by_count":17},{"id":"2002.07036","title":"Back-and-Forth prediction for deep tensor compression","created":"2020-02-14","cited_by_count":16},{"id":"2111.12166","title":"Towards Empirical Sandwich Bounds on the Rate-Distortion Function","created":"2021-11-23","cited_by_count":14},{"id":"1607.08011","title":"Understanding the limits of LoRaWAN","created":"2016-07-27","cited_by_count":11},{"id":"2107.13136","title":"Insights from Generative Modeling for Neural Video Compression","created":"2021-07-28","cited_by_count":9}],"next_cursor":null}