Feature Affinity-Based Pseudo Labeling for Semi-Supervised Person Re-Identification
نویسندگان
چکیده
منابع مشابه
Semi-supervised learning for text classification using feature affinity regularization
Most conventional semi-supervised learning methods attempt to directly include unlabeled data into training objectives. This paper presents an alternative approach that learns feature affinity information from unlabeled data, which is incorporated into the training objective as regularization of a maximum entropy model. The regularization favors models for which correlated features have similar...
متن کاملPerson Re-identification via Recurrent Feature Aggregation
We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framewor...
متن کاملfor “ Scalable Person Re - identification on Supervised Smoothed Manifold ”
The document contains the supplementary materials for “Scalable Person Re-identification on Supervised Smoothed Manifold”. Due to the space limitation, the comparison with state-of-the-art on PRID450S dataset [4] has to be simplified in the main paper. The only goal of this document is to present this comparison in Table 1. As can be seen, SSM sets a new state-of-the-art performance on this dat...
متن کاملEnd-user feature labeling: Supervised and semi-supervised approaches based on locally-weighted logistic regression
When intelligent interfaces, such as intelligent desktop assistants, email classifiers, and recommender systems, customize themselves to a particular end user, such customizations can decrease productivity and increase frustration due to inaccurate predictions—especially in early stages when training data is limited. The end user can improve the learning algorithm by tediously labeling a substa...
متن کاملOn-the-fly feature importance mining for person re-identification
State-of-the-art person re-identification methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with generic weights, which are assumed to be universally and equally good for all individuals, independent of people's different appearances. In this study, we show that certain features play more important role than others under d...
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: IEEE Transactions on Multimedia
سال: 2019
ISSN: 1520-9210,1941-0077
DOI: 10.1109/tmm.2019.2916456