A GAN-Based Self-Training Framework for Unsupervised Domain Adaptive Person Re-Identification
نویسندگان
چکیده
منابع مشابه
Query Based Adaptive Re-ranking for Person Re-identification
Existing algorithms for person re-identification hardly model query variations across non-overlapping cameras. In this paper, we propose a query based adaptive re-ranking method to address this important issue. In our work, negative image pairs can be easily generated for each query under non-overlapping cameras. To infer query variations across cameras, nearest neighbors of the query positive ...
متن کاملPerson Transfer GAN to Bridge Domain Gap for Person Re-Identification
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. To facilitate the research towards conquering those issues, this paper contributes a new datase...
متن کاملPerson re-identification by unsupervised video matching
Most existing person re-identification (ReID) methods rely only on the spatial appearance information from either one or multiple person images, whilst ignore the space-time cues readily available in video or imagesequence data. Moreover, they often assume the availability of exhaustively labelled cross-view pairwise data for every camera pair, making them non-scalable to ReID applications in r...
متن کاملUnsupervised Learning of Generative Topic Saliency for Person Re-identification
Existing approaches to person re-identification (re-id) are dominated by supervised learning based methods which focus on learning optimal similarity distance metrics. However, supervised learning based models require a large number of manually labelled pairs of person images across every pair of camera views. This thus limits their ability to scale to large camera networks. To overcome this pr...
متن کاملImage-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a “learning via translation” framework. In the baseline, we translate the labeled images from source to target domain in an unsupervised manner. We then train re-ID models with the translated images by supervised methods. Yet, being an essential part of this framewo...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Imaging
سال: 2021
ISSN: 2313-433X
DOI: 10.3390/jimaging7040062