Data to 7 Oct 2026

Unsupervised Domain Adaptation by Backpropagation

arXiv 1409.7495 ↗First posted 26 Sep 2014stat.ML cs.LG cs.NEcited by 1,906

Not on the map. Why?

Cited by 25 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of "deep" features that are (i) discriminative for the main learning task on the source domain and (ii) invariant with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a simple new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation. Overall, the approach can be implemented with little effort using any of the deep-learning packages. The method performs very well in a series of image classification experiments, achieving adaptation effect in the presence of big domain shifts and outperforming previous state-of-the-art on Office datasets.

Key facts. Cited by 1,906 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Sep 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 3; 2021: 441; 2022: 423; 2023: 387; 2024: 299; 2025: 222; 2026: 130.

1,906 papers.

Sort:

By area:

2024Depth Anything V2cited by 1,385
2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
2021Domain Generalization: A Surveycited by 760
2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
2021Domain Generalization with MixStylecited by 563
2022Continual Test-Time Domain Adaptationcited by 520
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
2021A Fourier-based Framework for Domain Generalizationcited by 287
2022Contrastive Test-Time Adaptationcited by 258

38 more

2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Modelscited by 222
2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
2021Trustworthy AI: From Principles to Practicescited by 206
2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
2021Self-Supervised Learning of Graph Neural Networks: A Unified Reviewcited by 184
2022Parameter-free Online Test-time Adaptationcited by 184
2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 177
2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
2021Learning to Diversify for Single Domain Generalizationcited by 170
2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 168
2023Multi-modal Learning with Missing Modality via Shared-Specific Feature Modellingcited by 159
2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153
2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
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
2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
2022Domain Adaptation via Prompt Learningcited by 128
2021Cross-Domain Adaptive Teacher for Object Detectioncited by 125
2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
2021Learning to Track with Object Permanencecited by 117
2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
2021Source-free Domain Adaptation via Avatar Prototype Generation and Adaptationcited by 111
2022Disentangled Representation Learningcited by 111
2022Curriculum Temperature for Knowledge Distillationcited by 110
2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
2022Linear Adversarial Concept Erasurecited by 98
2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
2022Visual Prompt Tuning for Test-time Domain Adaptationcited by 97
2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93

50 most cited of 1,906 All 1,906 (JSON)