{"list":"other","total":66,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"1910.12656","title":"Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration","created":"2019-10-28","cited_by_count":364},{"id":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1905.11001","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","created":"2019-05-27","cited_by_count":305},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"2003.07329","title":"Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning","created":"2020-03-16","cited_by_count":190},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"1808.05587","title":"Deep Convolutional Networks as shallow Gaussian Processes","created":"2018-08-16","cited_by_count":138},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117},{"id":"2006.12800","title":"Calibration of Neural Networks using Splines","created":"2020-06-23","cited_by_count":97},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97},{"id":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96},{"id":"2011.12562","title":"Delving Deep into Label Smoothing","created":"2020-11-25","cited_by_count":94},{"id":"2006.05065","title":"Self-Distillation as Instance-Specific Label Smoothing","created":"2020-06-09","cited_by_count":71},{"id":"2012.10988","title":"Post-hoc Uncertainty Calibration for Domain Drift Scenarios","created":"2020-12-20","cited_by_count":61},{"id":"2110.02473","title":"The Power of Contrast for Feature Learning: A Theoretical Analysis","created":"2021-10-06","cited_by_count":53},{"id":"2201.00057","title":"Optimal Representations for Covariate Shift","created":"2021-12-31","cited_by_count":51},{"id":"2102.06605","title":"Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning","created":"2021-02-12","cited_by_count":50},{"id":"2207.06211","title":"Sample-dependent Adaptive Temperature Scaling for Improved Calibration","created":"2022-07-13","cited_by_count":48},{"id":"2003.00343","title":"Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation","created":"2020-02-29","cited_by_count":43},{"id":"2302.06232","title":"Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data","created":"2023-02-13","cited_by_count":43},{"id":"2206.02757","title":"Robust Calibration with Multi-domain Temperature Scaling","created":"2022-06-06","cited_by_count":39},{"id":"2303.10720","title":"Trainable Projected Gradient Method for Robust Fine-tuning","created":"2023-03-19","cited_by_count":37},{"id":"1712.05902","title":"NSML: A Machine Learning Platform That Enables You to Focus on Your Models","created":"2017-12-16","cited_by_count":34},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34},{"id":"2306.04272","title":"On the Generalization of Multi-modal Contrastive Learning","created":"2023-06-07","cited_by_count":30},{"id":"2203.03897","title":"Geodesic Multi-Modal Mixup for Robust Fine-Tuning","created":"2022-03-08","cited_by_count":29},{"id":"2211.16175","title":"Context-Aware Robust Fine-Tuning","created":"2022-11-29","cited_by_count":28},{"id":"2104.00742","title":"Confidence Calibration for Domain Generalization under Covariate Shift","created":"2021-04-01","cited_by_count":27},{"id":"2104.08945","title":"Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation","created":"2021-04-18","cited_by_count":22},{"id":"2211.11719","title":"First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains","created":"2022-11-21","cited_by_count":21},{"id":"2310.19182","title":"Fast Trainable Projection for Robust Fine-Tuning","created":"2023-10-29","cited_by_count":19}],"next_cursor":null}