Year: 2025
Type: conference-paper
Abstract: Recently, diffusion models have garnered much attention for their remarkable generative capabilities. Yet, their application for representation learning remains largely unexplored. In this paper, we explore the potential of diffusion models to pretrain the backbone of a deep learning model for a specific application—gait recognition in the wild. To do so, we condition a latent diffusion model on the output of a gait recognition model backbone. Our pretraining experiments on the Gait3D and GREW datasets reveal an interesting phenomenon: diffusion pretraining causes the gait recognition backbone to separate gait sequences belonging to different subjects further apart than those belonging to the same subjects. Subsequently, our transfer learning experiments on Gait3D and GREW show that the pretrained backbone can serve as an effective initialization for the downstream gait recognition task, improving gait recognition accuracies by as much as 7.9% on Gait3D and 4.2% on GREW.
Authors: Wei Ming Neo, Koichi Shinoda, Tat-Jen Cham
Institutions: Nanyang Technological University, Institute of Science Tokyo
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
Award: 深層生成モデルを活用した構成的なパターン認識・理解
OpenAlex ID: W4413277991