MIC: Masked image consistency for context-enhanced domain adaptation

L Hoyer, D Dai, H Wang… - Proceedings of the IEEE …, 2023‏ - openaccess.thecvf.com
In unsupervised domain adaptation (UDA), a model trained on source data (eg synthetic) is
adapted to target data (eg real-world) without access to target annotation. Most previous …

Sepico: Semantic-guided pixel contrast for domain adaptive semantic segmentation

B **e, S Li, M Li, CH Liu, G Huang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on
an unlabeled target domain by utilizing the supervised model trained on a labeled source …

Model adaptation: Historical contrastive learning for unsupervised domain adaptation without source data

J Huang, D Guan, A **ao, S Lu - Advances in neural …, 2021‏ - proceedings.neurips.cc
Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled
target domain, but it requires to access the source data which often raises concerns in data …

Polarmix: A general data augmentation technique for lidar point clouds

A **ao, J Huang, D Guan, K Cui… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously,
capture precise geometry of the surrounding environment and are crucial to many …

3d semantic segmentation in the wild: Learning generalized models for adverse-condition point clouds

A **ao, J Huang, W Xuan, R Ren… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in
autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) …

Aloft: A lightweight mlp-like architecture with dynamic low-frequency transform for domain generalization

J Guo, N Wang, L Qi, Y Shi - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Abstract Domain generalization (DG) aims to learn a model that generalizes well to unseen
target domains utilizing multiple source domains without re-training. Most existing DG works …

Eventdance: Unsupervised source-free cross-modal adaptation for event-based object recognition

X Zheng, L Wang - … of the IEEE/CVF Conference on …, 2024‏ - openaccess.thecvf.com
In this paper we make the first attempt at achieving the cross-modal (ie image-to-events)
adaptation for event-based object recognition without accessing any labeled source image …

Padclip: Pseudo-labeling with adaptive debiasing in clip for unsupervised domain adaptation

Z Lai, N Vesdapunt, N Zhou, J Wu… - Proceedings of the …, 2023‏ - openaccess.thecvf.com
Abstract Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source
domain to tackle the learning tasks on the unlabeled target domain. It can be more …

Deformation depth decoupling network for point cloud domain adaptation

H Zhang, X Ning, C Wang, E Ning, L Li - Neural Networks, 2024‏ - Elsevier
Recently, point cloud domain adaptation (DA) practices have been implemented to improve
the generalization ability of deep learning models on point cloud data. However, variations …

Pipa: Pixel-and patch-wise self-supervised learning for domain adaptative semantic segmentation

M Chen, Z Zheng, Y Yang, TS Chua - Proceedings of the 31st ACM …, 2023‏ - dl.acm.org
Unsupervised Domain Adaptation (UDA) aims to enhance the generalization of the learned
model to other domains. The domain-invariant knowledge is transferred from the model …