{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"1706.00384","title":"Deep Mutual Learning","created":"2017-06-01","cited_by_count":628},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"1904.06487","title":"Semi-supervised Domain Adaptation via Minimax Entropy","created":"2019-04-13","cited_by_count":335},{"id":"2104.09044","title":"Distilling Knowledge via Knowledge Review","created":"2021-04-19","cited_by_count":288},{"id":"2006.10963","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","created":"2020-06-19","cited_by_count":236},{"id":"1905.10083","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing","created":"2019-05-24","cited_by_count":228},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"1904.01186","title":"Data-Free Learning of Student Networks","created":"2019-04-02","cited_by_count":204},{"id":"1612.03079","title":"Clipper: A Low-Latency Online Prediction Serving System","created":"2016-12-09","cited_by_count":191},{"id":"2201.05718","title":"Parameter-free Online Test-time Adaptation","created":"2022-01-15","cited_by_count":189},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"1702.03275","title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","created":"2017-02-10","cited_by_count":128},{"id":"1912.00350","title":"Online Knowledge Distillation with Diverse Peers","created":"2019-12-01","cited_by_count":128},{"id":"2106.15326","title":"Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation","created":"2021-06-18","cited_by_count":111},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107},{"id":"2107.09249","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","created":"2021-07-20","cited_by_count":95},{"id":"1712.06139","title":"TensorFlow-Serving: Flexible, High-Performance ML Serving","created":"2017-12-17","cited_by_count":85},{"id":"2012.11460","title":"SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation","created":"2020-12-21","cited_by_count":78},{"id":"1903.03215","title":"Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss","created":"2019-03-07","cited_by_count":67},{"id":"2103.16201","title":"MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaption","created":"2021-03-30","cited_by_count":65},{"id":"2012.08674","title":"Wasserstein Contrastive Representation Distillation","created":"2020-12-15","cited_by_count":64},{"id":"2007.07222","title":"Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis","created":"2020-07-05","cited_by_count":60},{"id":"2112.02355","title":"SITA: Single Image Test-time Adaptation","created":"2021-12-04","cited_by_count":59},{"id":"2110.11478","title":"MixNorm: Test-Time Adaptation Through Online Normalization Estimation","created":"2021-10-21","cited_by_count":47},{"id":"2209.05227","title":"DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization","created":"2022-09-12","cited_by_count":35},{"id":"2207.10856","title":"Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation","created":"2022-07-22","cited_by_count":33},{"id":"2107.13741","title":"Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels","created":"2021-07-29","cited_by_count":32},{"id":"1802.03151","title":"Deep Private-Feature Extraction","created":"2018-02-09","cited_by_count":30},{"id":"2209.04996","title":"Switchable Online Knowledge Distillation","created":"2022-09-12","cited_by_count":29},{"id":"1809.03428","title":"Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud","created":"2018-09-10","cited_by_count":28},{"id":"1605.07651","title":"Self Paced Deep Learning for Weakly Supervised Object Detection","created":"2016-05-24","cited_by_count":25},{"id":"1806.09856","title":"Dropout-based Active Learning for Regression","created":"2018-06-26","cited_by_count":24},{"id":"1807.01028","title":"Kitting in the Wild through Online Domain Adaptation","created":"2018-07-03","cited_by_count":24},{"id":"2104.09866","title":"Distill on the Go: Online knowledge distillation in self-supervised learning","created":"2021-04-20","cited_by_count":22},{"id":"2210.08884","title":"HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks","created":"2022-10-17","cited_by_count":19},{"id":"2310.19011","title":"Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction","created":"2023-10-29","cited_by_count":18},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12},{"id":"2208.10139","title":"Rethinking Knowledge Distillation via Cross-Entropy","created":"2022-08-22","cited_by_count":9}],"next_cursor":null}