most citedBeyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation

49 citations · 49 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2020

Interpreting Galaxy Deblender GAN from the Discriminator's Perspective

Heyi Li, Yuewei Lin, Klaus Mueller +1

Generative adversarial networks (GANs) are well known for their unsupervised learning capabilities. A recent success in the field of astronomy is deblending two overlapping galaxy…

cs.CV2017★ 49 cited

Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation

Heyi Li, Yunke Tian, Klaus Mueller +1

Despite the tremendous achievements of deep convolutional neural networks (CNNs) in many computer vision tasks, understanding how they actually work remains a significant challenge…