Diffusion Pretraining for Gait Recognition in the Wild

Wei Ming Neo, Koichi Shinoda, Tat-Jen Cham

Keywords: Diffusion Models, Gait Recognition, Representation Learning

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 possibility of using the diffusion process 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, which translates to a steady improvement in gait recognition performance. 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, allowing the gait recognition model to achieve better performance within much fewer supervised training iterations. We validated the applicability of our approach across multiple existing gait recognition methods and conducted extensive ablation studies to investigate the impact of different pretraining hyperparameters on the final gait recognition performance.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2184