{"list":"other","total":51,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2110.14795","title":"MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification","created":"2021-10-27","cited_by_count":690},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400},{"id":"2109.12298","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","created":"2021-09-25","cited_by_count":383},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","created":"2019-02-11","cited_by_count":267},{"id":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224},{"id":"1805.06530","title":"Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising","created":"2018-05-16","cited_by_count":218},{"id":"2010.14925","title":"MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis","created":"2020-10-28","cited_by_count":206},{"id":"2106.02848","title":"Numerical Composition of Differential Privacy","created":"2021-06-05","cited_by_count":180},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2007.14191","title":"Tempered Sigmoid Activations for Deep Learning with Differential Privacy","created":"2020-07-28","cited_by_count":122},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88},{"id":"2102.12677","title":"Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning","created":"2021-02-25","cited_by_count":86},{"id":"2302.13861","title":"Differentially Private Diffusion Models Generate Useful Synthetic Images","created":"2023-02-27","cited_by_count":86},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83},{"id":"2210.00038","title":"Differentially Private Optimization on Large Model at Small Cost","created":"2022-09-30","cited_by_count":65},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52},{"id":"1412.8659","title":"Deep Roto-Translation Scattering for Object Classification","created":"2014-12-30","cited_by_count":50},{"id":"2112.00193","title":"Public Data-Assisted Mirror Descent for Private Model Training","created":"2021-12-01","cited_by_count":49},{"id":"2207.00160","title":"When Does Differentially Private Learning Not Suffer in High Dimensions?","created":"2022-07-01","cited_by_count":48},{"id":"2202.05963","title":"Private Adaptive Optimization with Side Information","created":"2022-02-12","cited_by_count":38},{"id":"1901.09335","title":"Augment your batch: better training with larger batches","created":"2019-01-27","cited_by_count":37},{"id":"2302.09483","title":"Why Is Public Pretraining Necessary for Private Model Training?","created":"2023-02-19","cited_by_count":37},{"id":"2106.07830","title":"On the Convergence and Calibration of Deep Learning with Differential Privacy","created":"2021-06-15","cited_by_count":36},{"id":"2103.01439","title":"Fast Adaptation with Linearized Neural Networks","created":"2021-03-02","cited_by_count":32},{"id":"2004.05529","title":"Gradients as Features for Deep Representation Learning","created":"2020-04-12","cited_by_count":30},{"id":"2211.16412","title":"Procedural Image Programs for Representation Learning","created":"2022-11-29","cited_by_count":28},{"id":"2203.00324","title":"Differentially private training of residual networks with scale normalisation","created":"2022-03-01","cited_by_count":26},{"id":"2110.06255","title":"Not all noise is accounted equally: How differentially private learning benefits from large sampling rates","created":"2021-10-12","cited_by_count":21},{"id":"2301.13334","title":"A Bias-Accuracy-Privacy Trilemma for Statistical Estimation","created":"2023-01-30","cited_by_count":12},{"id":"2306.03962","title":"PILLAR: How to make semi-private learning more effective","created":"2023-06-06","cited_by_count":10},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7},{"id":"2209.04338","title":"Bridging the Gap: Differentially Private Equivariant Deep Learning for Medical Image Analysis","created":"2022-09-09","cited_by_count":2}],"next_cursor":null}