Unsupervised Domain Adaptation

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

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.

Unsupervised Domain Adaptation

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

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.

Semantic Segmentation Unsupervised Domain Adaptation

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

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.

Transfer Learning Unsupervised Domain Adaptation

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

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.

Unsupervised Domain Adaptation Unsupervised Person Re-Identification