A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification

2019-04-06 · ICCV 2019 10 · Lei Qi, Lei Wang, Jing Huo, Luping Zhou, Yinghuan Shi, Yang Gao

Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are addressed in this paper from the perspective of representation learning. For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains. For the second issue, we exploit the temporal continuity in each camera of target domain to create discriminative information. This is implemented by dynamically generating online triplets within each batch, in order to maximally take advantage of the steadily improved feature representation in training process. Together, the above two methods give rise to a novel unsupervised deep domain adaptation framework for person Re-ID. Experiments and ablation studies on benchmark datasets demonstrate its superiority and interesting properties.

📄 PDF Abstract BibTeX arXiv:1904.03425

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Person Re-Identification Representation Learning Unsupervised Domain Adaptation

Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation

2021-10-21 · Jiaming Zhang, Chaoxiang Ma, Kailun Yang, Alina Roitberg 외

Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360-degree sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic…

Autonomous Vehicles Domain Adaptation Segmentation Semantic Segmentation+1

Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification

2021-09-14 · Jongmin Yu, Junsik Kim, Minkyung Kim, Hyeontaek Oh

Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In constructing the dataset, assigning glo…

Contrastive Learning Domain Adaptation Unsupervised Vehicle Re-Identification Vehicle Re-Identification

From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras

2025-07-30 · Youngho Kim, Hoonhee Cho, Kuk-Jin Yoon arxiv

Human pose estimation is critical for applications such as rehabilitation, sports analytics, and AR/VR systems. However, rapid motion and low-light conditions often introduce motion blur, significantly degrading pose est…

Unsupervised Domain Adaptation 2D Human Pose Estimation

DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange

2021-08-13 · Chaoxiang Ma, Jiaming Zhang, Kailun Yang, Alina Roitberg 외

Intelligent vehicles clearly benefit from the expanded Field of View (FoV) of the 360-degree sensors, but the vast majority of available semantic segmentation training images are captured with pinhole cameras. In this wo…

Domain Adaptation Segmentation Semantic Segmentation Unsupervised Domain Adaptation

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

2021-03-08 · CVPR 2021 1 · Fengxiang Yang, Zhun Zhong, Zhiming Luo, Yuanzheng Cai 외

This paper considers the problem of unsupervised person re-identification (re-ID), which aims to learn discriminative models with unlabeled data. One popular method is to obtain pseudo-label by clustering and use them to…

Clustering Meta-Learning Person Re-Identification Pseudo Label+1