Towards Efficient U-Nets: A Coupled and Quantized Approach.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 30932829.
- Also identified by DOI 10.1109/TPAMI.2019.2907634.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
In this paper, we propose to couple stacked U-Nets for efficient visual landmark localization. The key idea is to globally reuse features of the same semantic meanings across the stacked U-Nets. The feature reuse makes each U-Net light-weighted. Specially, we propose an order- K coupling design to trim off long-distance shortcuts, together with an iterative refinement and memory sharing mechanism. To further improve the efficiency, we quantize the parameters, intermediate features, and gradients of the coupled U-Nets to low bit-width numbers. We validate our approach in two tasks: human pose estimation and facial landmark localization. The results show that our approach achieves state-of-the-art localization accuracy but using ∼ 70% fewer parameters, ∼ 30% less inference time, ∼ 98% less model size, and saving ∼ 75% training memory compared with benchmark localizers.