{"list":"other","total":57,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","created":"2014-02-08","cited_by_count":381},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1907.13625","title":"On Mutual Information Maximization for Representation Learning","created":"2019-07-31","cited_by_count":316},{"id":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"2102.08850","title":"Contrastive Learning Inverts the Data Generating Process","created":"2021-02-17","cited_by_count":221},{"id":"2002.07017","title":"Learning Robust Representations via Multi-View Information Bottleneck","created":"2020-02-17","cited_by_count":191},{"id":"1811.04251","title":"Formal Limitations on the Measurement of Mutual Information","created":"2018-11-10","cited_by_count":189},{"id":"2008.01064","title":"Predicting What You Already Know Helps: Provable Self-Supervised Learning","created":"2020-08-03","cited_by_count":152},{"id":"2205.11508","title":"Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods","created":"2022-05-23","cited_by_count":149},{"id":"2001.09122","title":"Reasoning About Generalization via Conditional Mutual Information","created":"2020-01-24","cited_by_count":147},{"id":"1710.05468","title":"Generalization in Deep Learning","created":"2017-10-16","cited_by_count":146},{"id":"1611.01353","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","created":"2016-11-04","cited_by_count":132},{"id":"1802.09766","title":"Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle","created":"2018-02-27","cited_by_count":70},{"id":"2203.07004","title":"Rethinking Minimal Sufficient Representation in Contrastive Learning","created":"2022-03-14","cited_by_count":69},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2205.10279","title":"Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors","created":"2022-05-20","cited_by_count":43},{"id":"1905.12213","title":"Where is the Information in a Deep Neural Network?","created":"2019-05-29","cited_by_count":42},{"id":"2109.12909","title":"Compressive Visual Representations","created":"2021-09-27","cited_by_count":41},{"id":"1706.02419","title":"Estimating Mixture Entropy with Pairwise Distances","created":"2017-06-08","cited_by_count":36},{"id":"2010.15703","title":"Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks","created":"2020-10-29","cited_by_count":28},{"id":"2206.13497","title":"Robustness Implies Generalization via Data-Dependent Generalization Bounds","created":"2022-06-27","cited_by_count":23},{"id":"2202.06749","title":"Information Flow in Deep Neural Networks","created":"2022-02-10","cited_by_count":22},{"id":"1803.08071","title":"Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses","created":"2018-03-21","cited_by_count":15},{"id":"2207.10081","title":"What Do We Maximize in Self-Supervised Learning?","created":"2022-07-20","cited_by_count":15},{"id":"1911.09189","title":"Information in Infinite Ensembles of Infinitely-Wide Neural Networks","created":"2019-11-20","cited_by_count":14},{"id":"2006.04641","title":"The Dual Information Bottleneck","created":"2020-06-08","cited_by_count":14},{"id":"2203.11284","title":"A Contrastive Objective for Learning Disentangled Representations","created":"2022-03-21","cited_by_count":14},{"id":"2105.03705","title":"Understanding Neural Networks with Logarithm Determinant Entropy Estimator","created":"2021-05-08","cited_by_count":10},{"id":"1810.05728","title":"Estimating Information Flow in Deep Neural Networks","created":"2018-10-12","cited_by_count":7},{"id":"1811.10228","title":"Attentioned Convolutional LSTM InpaintingNetwork for Anomaly Detection in Videos","created":"2018-11-26","cited_by_count":1}],"next_cursor":null}