TL;DR
An Adaptive Controlled Mutual Learning framework to address the one-to-many association optimization issue, and an Ambiguous Semantic Modeling (ASM) task designed to leverage soft labels outputted from the teacher model, providing more flexible supervision alongside original hard labels from textual descriptions.
A new domain adaptive person re-ID model DELTA (Deep Cluster with Attention Method) based on the unsupervised learning is proposed, which is more flexible and does not require additional annotations on the target domain.
This work provides a systematic review of TBPS by formalizing the problem setting and presenting a structured taxonomy of representative methods along four key technical dimensions: external knowledge-based approaches that leverage semantic priors to alleviate the inherent modality gap between visual and textual data.
A new ITM framework that improves the model's discriminative performance by focusing on localized core attributes and has a better robustness in handling highly similar hard negatives, which provides a new way to address cross-modal hard sample discrimination.
This approach introduces a Paired-Guided Consistency Rectification (PCR) module that utilizes strictly paired data as reliable anchors to dynamically calibrate the confidence of unpaired samples, effectively suppressing noise from inconsistent associations under mild-to-moderate corruptions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
