Unsupervised Domain Adaptation

Edit

276 papers with code • 16 benchmarks • 18 datasets

Unsupervised Domain Adaptation is a learning framework to transfer knowledge learned from source domains with a large number of annotated training examples to target domains with unlabeled data only.

Source: Domain-Specific Batch Normalization for Unsupervised Domain Adaptation

Benchmarks

Add a Result

Dataset	Best Model	Paper Title	Compare
Duke to Market	AWB	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond	See all
Market to Duke	AWB	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond	See all
ImageNet-C	EfficientNet-L2+RPL	Adapting ImageNet-scale models to complex distribution shifts with self-learning	See all
Market to MSMT	AWB	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond	See all
Duke to MSMT	AWB	Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification and Beyond	See all
ImageNet-R	EfficientNet-L2 Noisy Student + RPL	Adapting ImageNet-scale models to complex distribution shifts with self-learning	See all
Office-Home	DANN [cite:JMLR16RevGrad]	Domain-Adversarial Training of Neural Networks	See all
Cityscapes to Foggy Cityscapes	SAPNet	Spatial Attention Pyramid Network for Unsupervised Domain Adaptation	See all
Office-Home (RS-UT imbalance)	Implicit Alignment (with MDD)	Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation	See all
PreSIL to KITTI	PointDAN	PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation	See all
SIM10K to BDD100K	CDN	Adapting Object Detectors with Conditional Domain Normalization	See all
VisDA2017	MDD+Implicit Alignment	Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation	See all
Office-31	MDD+Implicit Alignment	Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation	See all
Portraits (over time)	Gradual Self-Training (Small Conv)	Understanding Self-Training for Gradual Domain Adaptation	See all
MSCOCO to FLIR ADAS	SGADA	Self-training Guided Adversarial Domain Adaptation For Thermal Imagery	See all
ImageNet-A	EfficientNet-L2 NoisyStudent + RPL	Adapting ImageNet-scale models to complex distribution shifts with self-learning	See all

Show all 16 benchmarks

Collapse benchmarks

Datasets

Greatest papers with code

Domain Separation Networks

tensorflow/models • • NeurIPS 2016

However, by focusing only on creating a mapping or shared representation between the two domains, they ignore the individual characteristics of each domain.

Ranked #1 on Domain Adaptation on Synth Digits-to-SVHN

Unsupervised Domain Adaptation

70,757

Paper
Code

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

tensorflow/models • • CVPR 2017

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks.

Unsupervised Domain Adaptation

65,339

Paper
Code

FDA: Fourier Domain Adaptation for Semantic Segmentation

albumentations-team/albumentations • • CVPR 2020

We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other.

Ranked #12 on Domain Adaptation on SYNTHIA-to-Cityscapes

Semantic Segmentation Unsupervised Domain Adaptation

8,432

Paper
Code

Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning

jindongwang/transferlearning • • 25 Mar 2019

In this paper, we propose a unified Transfer Channel Pruning (TCP) approach for accelerating UDA models.

Transfer Learning Unsupervised Domain Adaptation

7,427

Paper
Code

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

jindongwang/transferlearning • • 19 Jul 2018

Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning.

Ranked #1 on Domain Adaptation on Office-Caltech-10

Transfer Learning Unsupervised Domain Adaptation

7,427

Paper
Code

A Survey of Unsupervised Deep Domain Adaptation

zhaoxin94/awsome-domain-adaptation • • 6 Dec 2018

Deep learning has produced state-of-the-art results for a variety of tasks.

Transfer Learning Unsupervised Domain Adaptation

3,027

Paper
Code

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

zhaoxin94/awesome-domain-adaptation • • 1 Sep 2020

To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.

Unsupervised Domain Adaptation

3,026

Paper
Code

Learning Generalisable Omni-Scale Representations for Person Re-Identification

KaiyangZhou/deep-person-reid • • 15 Oct 2019

An effective person re-identification (re-ID) model should learn feature representations that are both discriminative, for distinguishing similar-looking people, and generalisable, for deployment across datasets without any adaptation.

Ranked #1 on Unsupervised Person Re-Identification on MSMT17->Market-1501