Privacy-Preserving Clothing Classification using Vision Transformer for Thermal Comfort Estimation
Tatsuya Chuman, Yousuke Udagawa, Hitoshi Kiya
TLDR
This paper introduces a privacy-preserving Vision Transformer for clothing classification to estimate thermal comfort without accuracy loss.
Key contributions
- Develops a privacy-preserving clothing classification method for secure thermal comfort estimation.
- Employs Vision Transformer (ViT) to accurately estimate clothing insulation from images.
- Maintains high classification accuracy on encrypted images, matching performance on plain images.
- Enables secure occupant-centric control (OCC) systems by protecting image privacy.
Why it matters
This paper is crucial for advancing secure occupant-centric control systems. It demonstrates that privacy in camera-based thermal comfort estimation can be achieved without compromising classification accuracy. This enables safer and more effective smart building applications.
Original Abstract
A privacy-preserving clothing classification scheme is presented to enable secure occupant-centric control (OCC) systems. Although the utilization of camera images for HVAC control has been widely studied to optimize thermal comfort, privacy protection of occupant images has not been considered in prior works. While various privacy-preserving methods have been proposed for image classification, applying conventional schemes results in severe accuracy degradation. In this paper, we introduce a privacy-preserving classification method using Vision Transformer (ViT) applied to clothing insulation estimation. In an experiment using the DeepFashion dataset categorized by clothing insulation, while the conventional pixel-based method suffers a severe accuracy drop, our scheme maintains a high accuracy on encrypted images, showing no degradation from plain images across all categories.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.