{"list":"other","total":137,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"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":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1403.6652","title":"DeepWalk: Online Learning of Social Representations","created":"2014-03-26","cited_by_count":1547},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"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":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1904.04232","title":"A Closer Look at Few-shot Classification","created":"2019-04-08","cited_by_count":684},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1902.06162","title":"Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey","created":"2019-02-16","cited_by_count":657},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1503.03578","title":"LINE: Large-scale Information Network Embedding","created":"2015-03-12","cited_by_count":582},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"2011.00362","title":"A Survey on Contrastive Self-supervised Learning","created":"2020-10-31","cited_by_count":554},{"id":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2003.11539","title":"Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?","created":"2020-03-25","cited_by_count":437},{"id":"1705.02364","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","created":"2017-05-05","cited_by_count":432},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2007.00224","title":"Debiased Contrastive Learning","created":"2020-07-01","cited_by_count":356},{"id":"1905.03670","title":"S4L: Self-Supervised Semi-Supervised Learning","created":"2019-05-09","cited_by_count":335},{"id":"2010.10144","title":"Keystroke Dynamics as Part of Lifelogging","created":"2020-10-20","cited_by_count":334},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1506.06726","title":"Skip-Thought Vectors","created":"2015-06-22","cited_by_count":322},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"1907.13625","title":"On Mutual Information Maximization for Representation Learning","created":"2019-07-31","cited_by_count":316},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"1406.6909","title":"Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks","created":"2014-06-26","cited_by_count":300},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"1905.11485","title":"Representation Learning for Dynamic Graphs: A Survey","created":"2019-05-27","cited_by_count":265},{"id":"1709.07604","title":"A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications","created":"2017-09-22","cited_by_count":260},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256},{"id":"1901.09005","title":"Revisiting Self-Supervised Visual Representation Learning","created":"2019-01-25","cited_by_count":251},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"1712.09405","title":"Advances in Pre-Training Distributed Word Representations","created":"2017-12-26","cited_by_count":207},{"id":"1905.01235","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","created":"2019-05-03","cited_by_count":201},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"id":"1710.02971","title":"Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec","created":"2017-10-09","cited_by_count":198},{"id":"2103.01988","title":"Self-supervised Pretraining of Visual Features in the Wild","created":"2021-03-02","cited_by_count":198},{"id":"1505.06279","title":"The Benefit of Multitask Representation Learning","created":"2015-05-23","cited_by_count":195},{"id":"1705.02801","title":"Graph Embedding Techniques, Applications, and Performance: A Survey","created":"2017-05-08","cited_by_count":188},{"id":"2010.03622","title":"Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data","created":"2020-10-07","cited_by_count":180},{"id":"2008.01064","title":"Predicting What You Already Know Helps: Provable Self-Supervised Learning","created":"2020-08-03","cited_by_count":152},{"id":"2105.11084","title":"Unsupervised Speech Recognition","created":"2021-05-24","cited_by_count":148},{"id":"2008.10150","title":"Contrastive learning, multi-view redundancy, and linear models","created":"2020-08-24","cited_by_count":146},{"id":"1906.05186","title":"Boosting Few-Shot Visual Learning with Self-Supervision","created":"2019-06-12","cited_by_count":140},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"2006.06606","title":"What makes instance discrimination good for transfer learning?","created":"2020-06-11","cited_by_count":111},{"id":"2004.11829","title":"A survey on domain adaptation theory: learning bounds and theoretical guarantees","created":"2020-04-24","cited_by_count":109}],"next_cursor":"100"}