{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"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":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2111.09832","title":"Merging Models with Fisher-Weighted Averaging","created":"2021-11-18","cited_by_count":621},{"id":"2002.06440","title":"Federated Learning with Matched Averaging","created":"2020-02-15","cited_by_count":564},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2302.12400","title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","created":"2023-02-24","cited_by_count":415},{"id":"2212.09849","title":"Dataless Knowledge Fusion by Merging Weights of Language Models","created":"2022-12-19","cited_by_count":387},{"id":"1904.06487","title":"Semi-supervised Domain Adaptation via Minimax Entropy","created":"2019-04-13","cited_by_count":335},{"id":"2204.10377","title":"Contrastive Test-Time Adaptation","created":"2022-04-21","cited_by_count":261},{"id":"2006.10963","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","created":"2020-06-19","cited_by_count":236},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"2208.05117","title":"NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation","created":"2022-08-10","cited_by_count":151},{"id":"2303.01904","title":"EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization","created":"2023-03-03","cited_by_count":123},{"id":"2211.13081","title":"Robust Mean Teacher for Continual and Gradual Test-Time Adaptation","created":"2022-11-23","cited_by_count":104},{"id":"2212.04145","title":"Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation","created":"2022-12-08","cited_by_count":98},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91},{"id":"2207.11707","title":"Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes","created":"2022-07-24","cited_by_count":67},{"id":"2407.06322","title":"MagMax: Leveraging Model Merging for Seamless Continual Learning","created":"2024-07-08","cited_by_count":67},{"id":"2207.10792","title":"Test-Time Adaptation via Self-Training with Nearest Neighbor Information","created":"2022-07-08","cited_by_count":64},{"id":"2306.04344","title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","created":"2023-06-07","cited_by_count":58},{"id":"2306.05401","title":"RDumb: A simple approach that questions our progress in continual test-time adaptation","created":"2023-06-08","cited_by_count":53},{"id":"2110.04065","title":"Test-time Batch Statistics Calibration for Covariate Shift","created":"2021-10-06","cited_by_count":50},{"id":"2212.09713","title":"A Probabilistic Framework for Lifelong Test-Time Adaptation","created":"2022-12-19","cited_by_count":46},{"id":"2309.14949","title":"Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization","created":"2023-09-26","cited_by_count":34},{"id":"2312.12480","title":"Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation","created":"2023-12-19","cited_by_count":30},{"id":"2303.09792","title":"Exploring Sparse Visual Prompt for Domain Adaptive Dense Prediction","created":"2023-03-17","cited_by_count":28},{"id":"2402.08712","title":"BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation","created":"2024-02-13","cited_by_count":25},{"id":"2304.06461","title":"Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning","created":"2023-04-13","cited_by_count":20},{"id":"2306.07483","title":"Semi-supervised learning made simple with self-supervised clustering","created":"2023-06-13","cited_by_count":20},{"id":"2311.18193","title":"Persistent Test-time Adaptation in Recurring Testing Scenarios","created":"2023-11-30","cited_by_count":18},{"id":"2312.09486","title":"Unraveling Batch Normalization for Realistic Test-Time Adaptation","created":"2023-12-15","cited_by_count":10},{"id":"2405.16486","title":"Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation","created":"2024-05-26","cited_by_count":10},{"id":"2407.09367","title":"Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation","created":"2024-07-12","cited_by_count":9},{"id":"2404.10966","title":"Domain-Specific Block Selection and Paired-View Pseudo-Labeling for Online Test-Time Adaptation","created":"2024-04-17","cited_by_count":8},{"id":"1607.02480","title":"Real-Time Anomaly Detection for Streaming Analytics","created":"2016-07-08","cited_by_count":5}],"next_cursor":null}