Unsupervised Domain Adaptation

710 papers with code • 36 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

Latest papers with no code

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

no code yet • 25 Mar 2024

In this paper, we propose a novel hybrid pseudo-labeling framework for unsupervised event-based semantic segmentation, HPL-ESS, to alleviate the influence of noisy pseudo labels.

Adversarially Masked Video Consistency for Unsupervised Domain Adaptation

no code yet • 24 Mar 2024

The second is a Masked Consistency Learning module to learn class-discriminative representations.

Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation

no code yet • 22 Mar 2024

Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps.

PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation

no code yet • 19 Mar 2024

In this work, we address these challenges by leveraging the abundance of unlabeled data available.

Semantics, Distortion, and Style Matter: Towards Source-free UDA for Panoramic Segmentation

no code yet • 19 Mar 2024

However, the distinct projection discrepancies between source and target domains impede the direct knowledge transfer; thus, we propose a panoramic prototype adaptation module (PPAM) to integrate panoramic prototypes from the extracted knowledge for adaptation.

A Fourier Transform Framework for Domain Adaptation

no code yet • 12 Mar 2024

By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels.

CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

no code yet • 6 Mar 2024

Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution.

Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation

no code yet • 5 Mar 2024

Specifically, the image contextual information is utilized to prompt the language branch in a domain-agnostic and instance-conditioned way.

DDF: A Novel Dual-Domain Image Fusion Strategy for Remote Sensing Image Semantic Segmentation with Unsupervised Domain Adaptation

no code yet • 5 Mar 2024

Semantic segmentation of remote sensing images is a challenging and hot issue due to the large amount of unlabeled data.

Key Design Choices in Source-Free Unsupervised Domain Adaptation: An In-depth Empirical Analysis

no code yet • 25 Feb 2024

This study provides a comprehensive benchmark framework for Source-Free Unsupervised Domain Adaptation (SF-UDA) in image classification, aiming to achieve a rigorous empirical understanding of the complex relationships between multiple key design factors in SF-UDA methods.