{"list":"other","total":67,"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1412.3474","title":"Deep Domain Confusion: Maximizing for Domain Invariance","created":"2014-12-10","cited_by_count":600},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2110.09506","title":"MEMO: Test Time Robustness via Adaptation and Augmentation","created":"2021-10-18","cited_by_count":377},{"id":"2008.11687","title":"What is being transferred in transfer learning?","created":"2020-08-26","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":"1602.04433","title":"Unsupervised Domain Adaptation with Residual Transfer Networks","created":"2016-02-14","cited_by_count":341},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"1403.6382","title":"CNN Features off-the-shelf: an Astounding Baseline for Recognition","created":"2014-03-23","cited_by_count":316},{"id":"2007.08489","title":"Do Adversarially Robust ImageNet Models Transfer Better?","created":"2020-07-16","cited_by_count":316},{"id":"2010.07249","title":"Environment Inference for Invariant Learning","created":"2020-10-14","cited_by_count":306},{"id":"1911.03437","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","created":"2019-11-08","cited_by_count":254},{"id":"1812.03372","title":"What is the Effect of Importance Weighting in Deep Learning?","created":"2018-12-08","cited_by_count":251},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"1802.01483","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","created":"2018-02-05","cited_by_count":227},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"1806.00900","title":"Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced","created":"2018-06-04","cited_by_count":177},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"1811.08737","title":"SpotTune: Transfer Learning through Adaptive Fine-tuning","created":"2018-11-21","cited_by_count":168},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"2008.03156","title":"Better Fine-Tuning by Reducing Representational Collapse","created":"2020-08-06","cited_by_count":157},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"1909.11299","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","created":"2019-09-25","cited_by_count":141},{"id":"2002.10964","title":"Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs","created":"2020-02-25","cited_by_count":132},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2004.04668","title":"Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation","created":"2020-04-09","cited_by_count":102},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"1902.01996","title":"Are All Layers Created Equal?","created":"2019-02-06","cited_by_count":94},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90},{"id":"1911.03090","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","created":"2019-11-08","cited_by_count":89},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75},{"id":"2102.03983","title":"Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning","created":"2021-02-08","cited_by_count":72},{"id":"2002.11770","title":"Rethinking the Hyperparameters for Fine-tuning","created":"2020-02-19","cited_by_count":69},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69},{"id":"2105.07029","title":"Learning a Universal Template for Few-shot Dataset Generalization","created":"2021-05-14","cited_by_count":61},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"2012.04550","title":"In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness","created":"2020-12-08","cited_by_count":50},{"id":"2107.05446","title":"Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration","created":"2021-07-12","cited_by_count":50},{"id":"2002.08253","title":"Distance-Based Regularisation of Deep Networks for Fine-Tuning","created":"2020-02-19","cited_by_count":48},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48},{"id":"1912.00528","title":"The intriguing role of module criticality in the generalization of deep networks","created":"2019-12-02","cited_by_count":40},{"id":"1703.09580","title":"Early Stopping without a Validation Set","created":"2017-03-28","cited_by_count":39},{"id":"2010.01926","title":"Test-time Unsupervised Domain Adaptation","created":"2020-10-05","cited_by_count":37},{"id":"1912.06761","title":"Targeted transfer learning to improve performance in small medical physics datasets","created":"2019-12-14","cited_by_count":11},{"id":"2008.11995","title":"A Flexible Selection Scheme for Minimum-Effort Transfer Learning","created":"2020-08-27","cited_by_count":8},{"id":"1910.01769","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","created":"2019-10-04","cited_by_count":3}],"next_cursor":null}