Searching Efficient Neural Architecture With Multi-Resolution Fusion Transformer for Appearance-Based Gaze Estimation

Vikrant Nagpure, Kenji Okuma; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 890-899

For aiming at a more accurate appearance-based gaze estimation, a series of recent works propose to use transformers or high-resolution networks in several ways which achieve state-of-the-art, but such works lack efficiency for real-time applications on edge computing devices. In this paper, we propose a compact model to precisely and efficiently solve gaze estimation. The proposed model includes 1) a Neural Architecture Search(NAS)-based multi-resolution feature extractor for extracting feature maps with global and local information which are essential for this task and 2) a novel multi-resolution fusion transformer as the gaze estimation head for efficiently estimating gaze values by fusing the extracted feature maps. We search our proposed model, called GazeNAS-ETH, on the ETH-XGaze dataset. We confirmed through experiments that GazeNAS-ETH achieved state-of-the-art on Gaze360, MPIIFaceGaze, RTGENE, and EYEDIAP datasets, while having only about 1M parameters and using only 0.28 GFLOPs, which is significantly less compared to previous state-of-the-art models, making it easier to deploy for real-time applications.