Unsupervised Domain Adaptation

673 papers with code • 31 benchmarks • 31 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

Libraries

Use these libraries to find Unsupervised Domain Adaptation models and implementations

Most implemented papers

Domain-Adversarial Training of Neural Networks

PaddlePaddle/PaddleSpeech 28 May 2015

Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification

heshuting555/TransReID CVPR 2018

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e. g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network.

Unsupervised Domain Adaptation by Backpropagation

PaddlePaddle/PaddleSpeech 26 Sep 2014

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).

Adversarial Discriminative Domain Adaptation

thuml/Transfer-Learning-Library CVPR 2017

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains.

Joint Discriminative and Generative Learning for Person Re-identification

layumi/Person_reID_baseline_pytorch CVPR 2019

To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.

Deep CORAL: Correlation Alignment for Deep Domain Adaptation

thuml/Transfer-Learning-Library 6 Jul 2016

CORAL is a "frustratingly easy" unsupervised domain adaptation method that aligns the second-order statistics of the source and target distributions with a linear transformation.

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

mil-tokyo/MCD_DA CVPR 2018

To solve these problems, we introduce a new approach that attempts to align distributions of source and target by utilizing the task-specific decision boundaries.

Domain Adaptive Faster R-CNN for Object Detection in the Wild

yuhuayc/da-faster-rcnn CVPR 2018

The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.

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.

Rescaling Egocentric Vision

epic-kitchens/epic-kitchens-100-annotations 23 Jun 2020

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS.