Attentional decoder networks for chest X-ray image recognition on high-resolution features

Hankyul Kang, Namkug Kim, Jongbin Ryu

Abstract: Highlights•We propose the AD-Net that utilizes a new encoder–decoder classification architecture.•We provide a harmonic magnitude transform that efficiently combines feature maps in a translation invariant manner, using minimal additional resources.•We achieve state-of-the-art performance on three widely-used chest X-ray datasets.