{"list":"other","total":82,"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"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":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"id":"1708.04896","title":"Random Erasing Data Augmentation","created":"2017-08-16","cited_by_count":1239},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"1612.03928","title":"Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer","created":"2016-12-12","cited_by_count":1077},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1805.09501","title":"AutoAugment: Learning Augmentation Policies from Data","created":"2018-05-24","cited_by_count":730},{"id":"1707.06168","title":"Channel Pruning for Accelerating Very Deep Neural Networks","created":"2017-07-19","cited_by_count":702},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"1810.05270","title":"Rethinking the Value of Network Pruning","created":"2018-10-11","cited_by_count":599},{"id":"1911.11236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","created":"2019-11-25","cited_by_count":585},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1907.09682","title":"Similarity-Preserving Knowledge Distillation","created":"2019-07-23","cited_by_count":516},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"1805.06085","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","created":"2018-05-16","cited_by_count":467},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","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":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"1904.01866","title":"A Comprehensive Overhaul of Feature Distillation","created":"2019-04-03","cited_by_count":348},{"id":"1906.04721","title":"Data-Free Quantization Through Weight Equalization and Bias Correction","created":"2019-06-11","cited_by_count":336},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"1812.08928","title":"Slimmable Neural Networks","created":"2018-12-21","cited_by_count":305},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"1811.03233","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","created":"2018-11-08","cited_by_count":238},{"id":"1903.10258","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","created":"2019-03-25","cited_by_count":227},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"1702.03044","title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights","created":"2017-02-10","cited_by_count":217},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"1905.05393","title":"Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules","created":"2019-05-14","cited_by_count":154},{"id":"2004.11886","title":"Lite Transformer with Long-Short Range Attention","created":"2020-04-24","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":"1903.12648","title":"Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild","created":"2019-03-29","cited_by_count":111},{"id":"1908.05005","title":"Benchmarking the Robustness of Semantic Segmentation Models","created":"2019-08-14","cited_by_count":111},{"id":"1903.12561","title":"Adversarial Robustness vs Model Compression, or Both?","created":"2019-03-29","cited_by_count":98},{"id":"1911.06987","title":"Faster AutoAugment: Learning Augmentation Strategies using Backpropagation","created":"2019-11-16","cited_by_count":96},{"id":"1912.13200","title":"AdderNet: Do We Really Need Multiplications in Deep Learning?","created":"2019-12-31","cited_by_count":82},{"id":"1809.05375","title":"Style Augmentation: Data Augmentation via Style Randomization","created":"2018-09-14","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":"2004.00448","title":"Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy","created":"2020-04-01","cited_by_count":66},{"id":"2003.03780","title":"DADA: Differentiable Automatic Data Augmentation","created":"2020-03-08","cited_by_count":57},{"id":"2008.11062","title":"GAN Slimming: All-in-One GAN Compression by A Unified Optimization Framework","created":"2020-08-25","cited_by_count":44},{"id":"1903.11752","title":"ThunderNet: Towards Real-time Generic Object Detection","created":"2019-03-28","cited_by_count":42},{"id":"2203.06321","title":"Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation","created":"2022-03-12","cited_by_count":39},{"id":"1905.07373","title":"Online Hyper-parameter Learning for Auto-Augmentation Strategy","created":"2019-05-17","cited_by_count":38},{"id":"2004.13866","title":"Deflating Dataset Bias Using Synthetic Data Augmentation","created":"2020-04-28","cited_by_count":38},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37},{"id":"2202.12513","title":"TeachAugment: Data Augmentation Optimization Using Teacher Knowledge","created":"2022-02-25","cited_by_count":37},{"id":"2009.08891","title":"AdderSR: Towards Energy Efficient Image Super-Resolution","created":"2020-09-18","cited_by_count":32},{"id":"2003.11342","title":"Circumventing Outliers of AutoAugment with Knowledge Distillation","created":"2020-03-25","cited_by_count":29},{"id":"2104.04282","title":"Direct Differentiable Augmentation Search","created":"2021-04-09","cited_by_count":28},{"id":"2108.06908","title":"Online Multi-Granularity Distillation for GAN Compression","created":"2021-08-16","cited_by_count":24},{"id":"2009.09152","title":"Weight Distillation: Transferring the Knowledge in Neural Network Parameters","created":"2020-09-19","cited_by_count":23},{"id":"2110.14439","title":"Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme","created":"2021-10-27","cited_by_count":23},{"id":"1906.03951","title":"SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models","created":"2019-05-27","cited_by_count":22},{"id":"1911.02237","title":"Localization-aware Channel Pruning for Object Detection","created":"2019-11-06","cited_by_count":13},{"id":"1911.13019","title":"Towards Oracle Knowledge Distillation with Neural Architecture Search","created":"2019-11-29","cited_by_count":13},{"id":"2104.15082","title":"Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation","created":"2021-04-30","cited_by_count":13},{"id":"2006.03810","title":"An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation","created":"2020-06-06","cited_by_count":11},{"id":"1903.01522","title":"TKD: Temporal Knowledge Distillation for Active Perception","created":"2019-03-04","cited_by_count":8},{"id":"2004.08861","title":"Role-Wise Data Augmentation for Knowledge Distillation","created":"2020-04-19","cited_by_count":8},{"id":"2104.00432","title":"Anchor Pruning for Object Detection","created":"2021-04-01","cited_by_count":5},{"id":"2002.06048","title":"AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks","created":"2020-02-14","cited_by_count":2}],"next_cursor":null}