Abstract
Low-resolution images present significant challenges for age estimation in real-world. Current models are unsuitable for low-resolution scenarios as they lose crucial details and weaken feature representations, leading to significant performance degradation. To address the limitation, we propose the Multi-Grained Pooling Network (MGP-Net), a novel architecture that effectively captures multi-grained information during the downsampling process, preserving essential features for age estimation. Additionally, we introduce a simple random shuffle degradation model to simulate realistic low-resolution images, ensuring robust training and evaluation. Experimental results on the Morph [Formula: see text], FG-NET, and CLAP2015 datasets demonstrate that the proposed method achieves competitive performance compared to the state-of-the-art models which trained with high-resolution images, showcasing its robustness and applicability in real-world low-resolution scenarios.