Data to 7 Oct 2026

Moment Matching for Multi-Source Domain Adaptation

arXiv 1812.01754 ↗First posted 4 Dec 2018cs.CVcited by 1,327

Not on the map. Why?

Cited by 67 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Conventional unsupervised domain adaptation (UDA) assumes that training data are sampled from a single domain. This neglects the more practical scenario where training data are collected from multiple sources, requiring multi-source domain adaptation. We make three major contributions towards addressing this problem. First, we collect and annotate by far the largest UDA dataset, called DomainNet, which contains six domains and about 0.6 million images distributed among 345 categories, addressing the gap in data availability for multi-source UDA research. Second, we propose a new deep learning approach, Moment Matching for Multi-Source Domain Adaptation M3SDA, which aims to transfer knowledge learned from multiple labeled source domains to an unlabeled target domain by dynamically aligning moments of their feature distributions. Third, we provide new theoretical insights specifically for moment matching approaches in both single and multiple source domain adaptation. Extensive experiments are conducted to demonstrate the power of our new dataset in benchmarking state-of-the-art multi-source domain adaptation methods, as well as the advantage of our proposed model. Dataset and Code are available at urlhttp://ai.bu.edu/M3SDA/.

Key facts. Cited by 1,327 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 170; 2022: 210; 2023: 295; 2024: 304; 2025: 225; 2026: 123.

1,327 papers.

Sort:

By area:

2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
2021Domain Generalization: A Surveycited by 760
2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
2022CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learningcited by 446
2021SWAD: Domain Generalization by Seeking Flat Minimacited by 431
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2021Deep Long-Tailed Learning: A Surveycited by 416
2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 259
2021Gradient Matching for Domain Generalizationcited by 258
2022Contrastive Test-Time Adaptationcited by 258

38 more

2022S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learningcited by 246
2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 189
2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
2023Robust Test-Time Adaptation in Dynamic Scenarioscited by 185
2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
2023SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Modelcited by 178
2021A Fine-Grained Analysis on Distribution Shiftcited by 171
2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 162
2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
2021Self-Supervised Models are Continual Learnerscited by 149
2022Diverse Weight Averaging for Out-of-Distribution Generalizationcited by 148
2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalizationcited by 144
2022ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Modelscited by 141
2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
2022Domain Generalization by Mutual-Information Regularization with Pre-trained Modelscited by 133
2023Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusioncited by 131
2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
2022Domain Adaptation via Prompt Learningcited by 128
2023A Unified Continual Learning Framework with General Parameter-Efficient Tuningcited by 124
2021Cycle Self-Training for Domain Adaptationcited by 120
2021Are Large-scale Datasets Necessary for Self-Supervised Pre-training?cited by 117
2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
2024Scalable Pre-training of Large Autoregressive Image Modelscited by 115
2024Multimodal Autoregressive Pre-training of Large Vision Encoderscited by 108
2021Efficient Training of Visual Transformers with Small Datasetscited by 107
2024Measuring Style Similarity in Diffusion Modelscited by 106
2021AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptationcited by 104
2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
2022Robust Mean Teacher for Continual and Gradual Test-Time Adaptationcited by 102
2023Sharpness-Aware Gradient Matching for Domain Generalizationcited by 102
2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
2022Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalizationcited by 97
2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96

50 most cited of 1,327 All 1,327 (JSON)