{"list":"other","total":84,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"2204.07141","title":"Masked Siamese Networks for Label-Efficient Learning","created":"2022-04-14","cited_by_count":302},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1803.08533","title":"Understanding Measures of Uncertainty for Adversarial Example Detection","created":"2018-03-22","cited_by_count":177},{"id":"2202.02794","title":"Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets","created":"2022-02-06","cited_by_count":133},{"id":"2010.09535","title":"Cold-start Active Learning through Self-supervised Language Modeling","created":"2020-10-19","cited_by_count":128},{"id":"2302.14545","title":"Modern Bayesian Experimental Design","created":"2023-02-28","cited_by_count":125},{"id":"2108.01775","title":"Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning","created":"2021-08-03","cited_by_count":116},{"id":"1910.07153","title":"Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost","created":"2019-10-16","cited_by_count":114},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101},{"id":"1806.05161","title":"Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate","created":"2018-06-13","cited_by_count":99},{"id":"1911.09162","title":"Deep Active Learning: Unified and Principled Method for Query and Training","created":"2019-11-20","cited_by_count":93},{"id":"2103.06191","title":"A Study of Face Obfuscation in ImageNet","created":"2021-03-10","cited_by_count":83},{"id":"1908.02144","title":"Bayesian Batch Active Learning as Sparse Subset Approximation","created":"2019-08-06","cited_by_count":68},{"id":"2205.11320","title":"Active Learning Through a Covering Lens","created":"2022-05-23","cited_by_count":66},{"id":"2211.06291","title":"Do Bayesian Neural Networks Need To Be Fully Stochastic?","created":"2022-11-11","cited_by_count":63},{"id":"2304.08151","title":"Prediction-Oriented Bayesian Active Learning","created":"2023-04-17","cited_by_count":62},{"id":"2011.12829","title":"All You Need is a Good Functional Prior for Bayesian Deep Learning","created":"2020-11-25","cited_by_count":61},{"id":"2004.04943","title":"State-Relabeling Adversarial Active Learning","created":"2020-04-10","cited_by_count":60},{"id":"2007.03196","title":"ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction","created":"2020-07-07","cited_by_count":58},{"id":"1904.11643","title":"Bayesian Generative Active Deep Learning","created":"2019-04-26","cited_by_count":57},{"id":"2008.05912","title":"A statistical theory of cold posteriors in deep neural networks","created":"2020-08-13","cited_by_count":54},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51},{"id":"2107.14153","title":"Semi-Supervised Active Learning with Temporal Output Discrepancy","created":"2021-07-29","cited_by_count":50},{"id":"2108.11458","title":"Reducing Label Effort: Self-Supervised meets Active Learning","created":"2021-08-25","cited_by_count":42},{"id":"1911.08177","title":"Rethinking deep active learning: Using unlabeled data at model training","created":"2019-11-19","cited_by_count":39},{"id":"1912.05361","title":"Parting with Illusions about Deep Active Learning","created":"2019-12-11","cited_by_count":38},{"id":"2203.07472","title":"Uncertainty Estimation for Language Reward Models","created":"2022-03-14","cited_by_count":37},{"id":"2106.12059","title":"Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning","created":"2021-06-22","cited_by_count":36},{"id":"2204.08491","title":"Active Learning Helps Pretrained Models Learn the Intended Task","created":"2022-04-18","cited_by_count":33},{"id":"2003.00393","title":"Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision","created":"2020-03-01","cited_by_count":32},{"id":"2104.08320","title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning","created":"2021-04-16","cited_by_count":32},{"id":"2111.12880","title":"Active Learning at the ImageNet Scale","created":"2021-11-25","cited_by_count":28},{"id":"2201.07459","title":"PT4AL: Using Self-Supervised Pretext Tasks for Active Learning","created":"2022-01-19","cited_by_count":27},{"id":"2301.10625","title":"Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment","created":"2023-01-25","cited_by_count":26},{"id":"2106.11719","title":"Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers","created":"2021-06-22","cited_by_count":22},{"id":"2110.04629","title":"The Neural Testbed: Evaluating Joint Predictions","created":"2021-10-09","cited_by_count":22},{"id":"2211.01568","title":"Fine-Tuning Language Models via Epistemic Neural Networks","created":"2022-11-03","cited_by_count":22},{"id":"1902.00925","title":"Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning","created":"2019-02-03","cited_by_count":21},{"id":"2011.03178","title":"Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?","created":"2020-11-06","cited_by_count":21},{"id":"2306.09910","title":"LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning","created":"2023-06-16","cited_by_count":20},{"id":"2011.08121","title":"On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?","created":"2020-11-16","cited_by_count":18},{"id":"2012.10467","title":"Minimax Active Learning","created":"2020-12-18","cited_by_count":18},{"id":"1903.02852","title":"Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models","created":"2019-03-07","cited_by_count":16},{"id":"2006.09916","title":"Bayesian active learning for production, a systematic study and a reusable library","created":"2020-06-17","cited_by_count":15},{"id":"2110.12033","title":"A Simple Baseline for Low-Budget Active Learning","created":"2021-10-22","cited_by_count":15},{"id":"1811.03575","title":"Large-Scale Visual Active Learning with Deep Probabilistic Ensembles","created":"2018-11-08","cited_by_count":13},{"id":"2302.08981","title":"Black-Box Batch Active Learning for Regression","created":"2023-02-17","cited_by_count":12},{"id":"2202.13509","title":"Evaluating High-Order Predictive Distributions in Deep Learning","created":"2022-02-28","cited_by_count":10},{"id":"2302.04075","title":"Best Practices in Active Learning for Semantic Segmentation","created":"2023-02-08","cited_by_count":10},{"id":"2010.15947","title":"PAL : Pretext-based Active Learning","created":"2020-10-29","cited_by_count":9},{"id":"1803.01216","title":"Deep Bayesian Active Semi-Supervised Learning","created":"2018-03-03","cited_by_count":7},{"id":"1912.09720","title":"Adversarial Representation Active Learning","created":"2019-12-20","cited_by_count":7},{"id":"2210.05770","title":"Deep Active Ensemble Sampling For Image Classification","created":"2022-10-11","cited_by_count":7},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7},{"id":"2112.06796","title":"Depth Uncertainty Networks for Active Learning","created":"2021-12-13","cited_by_count":2},{"id":"2301.09490","title":"Speeding Up BatchBALD: A k-BALD Family of Approximations for Active Learning","created":"2023-01-23","cited_by_count":2},{"id":"2211.06139","title":"Understanding Approximation for Bayesian Inference in Neural Networks","created":"2022-11-11","cited_by_count":1}],"next_cursor":null}