About

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

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Latest papers with code

Reproducibility of "FDA: Fourier Domain Adaptation forSemantic Segmentation

30 Apr 2021thefatbandit/FDA

The following paper is a reproducibility report for "FDA: Fourier Domain Adaptation for Semantic Segmentation" published in the CVPR 2020 as part of the ML Reproducibility Challenge 2020.

SEMANTIC SEGMENTATION UNSUPERVISED DOMAIN ADAPTATION

2
30 Apr 2021

Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation

29 Apr 2021Chao-Chen-Hao/Rethinking-EnD-SegUDA

Recent researches on unsupervised domain adaptation (UDA) have demonstrated that end-to-end ensemble learning frameworks serve as a compelling option for UDA tasks.

SEMANTIC SEGMENTATION UNSUPERVISED DOMAIN ADAPTATION

2
29 Apr 2021

Efficient Pre-trained Features and Recurrent Pseudo-Labeling in Unsupervised Domain Adaptation

27 Apr 2021YoushanZhang/Transfer-Learning

In this paper, we show how to efficiently opt for the best pre-trained features from seventeen well-known ImageNet models in unsupervised DA problems.

UNSUPERVISED DOMAIN ADAPTATION

0
27 Apr 2021

Visualizing Adapted Knowledge in Domain Transfer

20 Apr 2021hou-yz/DA_visualization

We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains.

EXPLAINABLE ARTIFICIAL INTELLIGENCE UNSUPERVISED DOMAIN ADAPTATION

11
20 Apr 2021

Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching

15 Apr 2021jindongwang/transferlearning

End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data.

SPEECH RECOGNITION UNSUPERVISED DOMAIN ADAPTATION

7,008
15 Apr 2021

FreSaDa: A French Satire Data Set for Cross-Domain Satire Detection

10 Apr 2021adrianchifu/FreSaDa

We employ two classification methods as baselines for our new data set, one based on low-level features (character n-grams) and one based on high-level features (average of CamemBERT word embeddings).

UNSUPERVISED DOMAIN ADAPTATION WORD EMBEDDINGS

1
10 Apr 2021

Distill and Fine-tune: Effective Adaptation from a Black-box Source Model

4 Apr 2021tim-learn/Dis-tune

To alleviate the burden of labeling, unsupervised domain adaptation (UDA) aims to transfer knowledge in previous related labeled datasets (source) to a new unlabeled dataset (target).

UNSUPERVISED DOMAIN ADAPTATION

1
04 Apr 2021

Unsupervised Domain Expansion for Visual Categorization

1 Apr 2021li-xirong/ude

In this paper we extend UDA by proposing a new task called unsupervised domain expansion (UDE), which aims to adapt a deep model for the target domain with its unlabeled data, meanwhile maintaining the model's performance on the source domain.

KNOWLEDGE DISTILLATION UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED DOMAIN EXPANSION

0
01 Apr 2021

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

31 Mar 2021zhengzangw/PCS-FUDA

In this paper, we propose an end-to-end Prototypical Cross-domain Self-Supervised Learning (PCS) framework for Few-shot Unsupervised Domain Adaptation (FUDA).

SELF-SUPERVISED LEARNING UNSUPERVISED DOMAIN ADAPTATION

10
31 Mar 2021

Cluster Contrast for Unsupervised Person Re-Identification

22 Mar 2021alibaba/cluster-contrast

We demonstrate that the inconsistency problem for cluster feature representation can be solved by the cluster-level memory dictionary. By straightforwardly applying Cluster Contrast to a standard unsupervised re-ID pipeline, it achieves considerable improvements of 9. 5%, 7. 5%, 6. 6% compared to state-of-the-art purely unsupervised re-ID methods and 5. 1%, 4. 0%, 6. 5% mAP compared to the state-of-the-art unsupervised domain adaptation re-ID methods on the Market, Duke, andMSMT17 datasets. Our source code is available at https://github. com/alibaba/cluster-contrast.

UNSUPERVISED DOMAIN ADAPTATION UNSUPERVISED PERSON RE-IDENTIFICATION

31
22 Mar 2021