{"list":"other","total":149,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1809.10341","title":"Deep Graph Infomax","created":"2018-09-27","cited_by_count":1106},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"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":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1712.02560","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","created":"2017-12-07","cited_by_count":683},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1811.12833","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","created":"2018-11-30","cited_by_count":623},{"id":"1605.06636","title":"Deep Transfer Learning with Joint Adaptation Networks","created":"2016-05-21","cited_by_count":612},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1803.03243","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","created":"2018-03-08","cited_by_count":443},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"1901.00976","title":"Contrastive Adaptation Network for Unsupervised Domain Adaptation","created":"2019-01-04","cited_by_count":407},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"1902.07208","title":"Transfusion: Understanding Transfer Learning for Medical Imaging","created":"2019-02-14","cited_by_count":368},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"2012.07463","title":"Parameter-Efficient Transfer Learning with Diff Pruning","created":"2020-12-14","cited_by_count":352},{"id":"1901.11504","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","created":"2019-01-31","cited_by_count":350},{"id":"1602.04433","title":"Unsupervised Domain Adaptation with Residual Transfer Networks","created":"2016-02-14","cited_by_count":341},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1711.04043","title":"Few-Shot Learning with Graph Neural Networks","created":"2017-11-10","cited_by_count":324},{"id":"1608.06019","title":"Domain Separation Networks","created":"2016-08-22","cited_by_count":320},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"1612.05424","title":"Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks","created":"2016-12-16","cited_by_count":308}],"next_cursor":"100"}