Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
Z Cui, J Zhou, X Wang, M Zhu… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Abstract Lifelong Person Re-identification (L-ReID) aims to learn from sequentially collected
data to match a person across different scenes. Once an L-ReID model is updated using …
data to match a person across different scenes. Once an L-ReID model is updated using …
MixBCT: Towards Self-Adapting Backward-Compatible Training
Y Liang, Y Zhang, S Zhang, Y Wang, S **ao… - arxiv preprint arxiv …, 2023 - arxiv.org
Backward-compatible training circumvents the need for expensive updates to the old gallery
database when deploying an advanced new model in the retrieval system. Previous …
database when deploying an advanced new model in the retrieval system. Previous …
Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer
Visual retrieval systems face significant challenges when updating models with improved
representations due to misalignment between the old and new representations. The costly …
representations due to misalignment between the old and new representations. The costly …
FC-Aligner: A Lightweight Regressor Model for Embedding Space Conversion
ALBV e Silva, RG Ferrari, ÁS Nolibos… - Latinx in AI@ NeurIPS … - openreview.net
In diverse applications like image clustering, facial recognition and text embeddings,
similarity search is critical. Deep models utilize feature embeddings for efficient …
similarity search is critical. Deep models utilize feature embeddings for efficient …