{"list":"other","total":152,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1608.08710","title":"Pruning Filters for Efficient ConvNets","created":"2016-08-31","cited_by_count":1143},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"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":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1812.04244","title":"PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud","created":"2018-12-11","cited_by_count":941},{"id":"1904.05068","title":"Relational Knowledge Distillation","created":"2019-04-10","cited_by_count":889},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1908.09355","title":"Patient Knowledge Distillation for BERT Model Compression","created":"2019-08-25","cited_by_count":508},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2106.01226","title":"Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision","created":"2021-06-02","cited_by_count":463},{"id":"1912.08795","title":"Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion","created":"2019-12-18","cited_by_count":423},{"id":"2105.10056","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","created":"2021-05-20","cited_by_count":383},{"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":"2104.07586","title":"See through Gradients: Image Batch Recovery via GradInversion","created":"2021-04-15","cited_by_count":326},{"id":"2004.05937","title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","created":"2020-04-13","cited_by_count":316},{"id":"1904.10620","title":"Bidirectional Learning for Domain Adaptation of Semantic Segmentation","created":"2019-04-24","cited_by_count":308},{"id":"2102.09480","title":"Unbiased Teacher for Semi-Supervised Object Detection","created":"2021-02-18","cited_by_count":306},{"id":"1802.05668","title":"Model compression via distillation and quantization","created":"2018-02-15","cited_by_count":289},{"id":"1903.04197","title":"Structured Knowledge Distillation for Dense Prediction","created":"2019-03-11","cited_by_count":279},{"id":"2001.00281","title":"ZeroQ: A Novel Zero Shot Quantization Framework","created":"2020-01-01","cited_by_count":269},{"id":"2004.02178","title":"FastBERT: a Self-distilling BERT with Adaptive Inference Time","created":"2020-04-05","cited_by_count":226},{"id":"1908.09884","title":"Learning to Discover Novel Visual Categories via Deep Transfer Clustering","created":"2019-08-26","cited_by_count":225},{"id":"2004.04393","title":"Universal Source-Free Domain Adaptation","created":"2020-04-09","cited_by_count":220},{"id":"2007.07936","title":"ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning","created":"2020-07-15","cited_by_count":209},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"2004.07703","title":"Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision","created":"2020-04-16","cited_by_count":198},{"id":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"id":"2110.04202","title":"Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation","created":"2021-10-08","cited_by_count":177},{"id":"2108.01614","title":"Generalized Source-free Domain Adaptation","created":"2021-08-03","cited_by_count":175},{"id":"2012.07297","title":"Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer","created":"2020-12-14","cited_by_count":173},{"id":"2103.16372","title":"Source-Free Domain Adaptation for Semantic Segmentation","created":"2021-03-30","cited_by_count":168},{"id":"1908.00821","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","created":"2019-08-02","cited_by_count":162},{"id":"1901.05335","title":"A review of domain adaptation without target labels","created":"2019-01-16","cited_by_count":156},{"id":"2110.03374","title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","created":"2021-10-07","cited_by_count":152},{"id":"1901.05427","title":"Domain Adaptation for Structured Output via Discriminative Patch Representations","created":"2019-01-16","cited_by_count":150},{"id":"1909.13589","title":"Domain Adaptation for Semantic Segmentation with Maximum Squares Loss","created":"2019-09-30","cited_by_count":138},{"id":"1710.07535","title":"Data-Free Knowledge Distillation for Deep Neural Networks","created":"2017-10-19","cited_by_count":136},{"id":"2106.09701","title":"Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning","created":"2021-06-17","cited_by_count":131},{"id":"1905.09768","title":"Zero-shot Knowledge Transfer via Adversarial Belief Matching","created":"2019-05-23","cited_by_count":129},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2011.14779","title":"Data-Free Model Extraction","created":"2020-11-30","cited_by_count":124},{"id":"1905.08114","title":"Zero-Shot Knowledge Distillation in Deep Networks","created":"2019-05-20","cited_by_count":121},{"id":"2103.01737","title":"Distilling Causal Effect of Data in Class-Incremental Learning","created":"2021-03-02","cited_by_count":117},{"id":"2106.10456","title":"Humble Teachers Teach Better Students for Semi-Supervised Object Detection","created":"2021-06-19","cited_by_count":116},{"id":"2103.04059","title":"Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning","created":"2021-03-06","cited_by_count":115},{"id":"2106.15326","title":"Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation","created":"2021-06-18","cited_by_count":111},{"id":"2006.12000","title":"Self-Knowledge Distillation with Progressive Refinement of Targets","created":"2020-06-22","cited_by_count":107},{"id":"1812.00123","title":"Snapshot Distillation: Teacher-Student Optimization in One Generation","created":"2018-12-01","cited_by_count":99},{"id":"2005.03161","title":"MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation","created":"2020-05-06","cited_by_count":99},{"id":"2102.09003","title":"Domain Impression: A Source Data Free Domain Adaptation Method","created":"2021-02-17","cited_by_count":91},{"id":"1912.11006","title":"Data-Free Adversarial Distillation","created":"2019-12-23","cited_by_count":90},{"id":"2003.03603","title":"Generative Low-bitwidth Data Free Quantization","created":"2020-03-07","cited_by_count":88},{"id":"2007.01524","title":"Domain Adaptation without Source Data","created":"2020-07-03","cited_by_count":88},{"id":"2108.11249","title":"Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation","created":"2021-08-25","cited_by_count":81},{"id":"2005.04136","title":"Data-Free Network Quantization With Adversarial Knowledge Distillation","created":"2020-05-08","cited_by_count":80},{"id":"2012.05400","title":"A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data","created":"2020-12-10","cited_by_count":79},{"id":"2101.08482","title":"Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning","created":"2021-01-21","cited_by_count":78},{"id":"1908.09511","title":"Relation Distillation Networks for Video Object Detection","created":"2019-08-26","cited_by_count":77},{"id":"1510.00726","title":"A Primer on Neural Network Models for Natural Language Processing","created":"2015-10-02","cited_by_count":76},{"id":"2104.01845","title":"Unsupervised Multi-source Domain Adaptation Without Access to Source Data","created":"2021-04-05","cited_by_count":76},{"id":"2103.14357","title":"VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation","created":"2021-03-26","cited_by_count":69},{"id":"1811.05419","title":"Fast Human Pose Estimation","created":"2018-11-13","cited_by_count":68},{"id":"1712.01048","title":"Adaptive Quantization for Deep Neural Network","created":"2017-12-04","cited_by_count":67},{"id":"1911.02888","title":"This dataset does not exist: training models from generated images","created":"2019-11-07","cited_by_count":65},{"id":"2004.06042","title":"Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation","created":"2020-04-13","cited_by_count":64},{"id":"2002.01775","title":"Feature-map-level Online Adversarial Knowledge Distillation","created":"2020-02-05","cited_by_count":62},{"id":"1809.07428","title":"Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System","created":"2018-09-19","cited_by_count":60},{"id":"2003.12703","title":"DaST: Data-free Substitute Training for Adversarial Attacks","created":"2020-03-28","cited_by_count":60},{"id":"1912.01274","title":"The Knowledge Within: Methods for Data-Free Model Compression","created":"2019-12-03","cited_by_count":54},{"id":"2005.03697","title":"Source-Relaxed Domain Adaptation for Image Segmentation","created":"2020-05-07","cited_by_count":52},{"id":"2107.05446","title":"Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration","created":"2021-07-12","cited_by_count":50},{"id":"2110.04065","title":"Test-time Batch Statistics Calibration for Covariate Shift","created":"2021-10-06","cited_by_count":50},{"id":"2102.11614","title":"Self-Supervised Noisy Label Learning for Source-Free Unsupervised Domain Adaptation","created":"2021-02-23","cited_by_count":47}],"next_cursor":"100"}