DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks

• Main Authors: Mukherjee, Prerana, Sharma, Manoj, Makwana, Megh, Singh, Ajay Pratap, Upadhyay, Avinash, Trivedi, Akkshita, Lall, Brejesh, Chaudhury, Santanu
• Format: Journal Article
• Language: English
• Published: 02-04-2019
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.1904.01215

Synthesizing high quality saliency maps from noisy images is a challenging
problem in computer vision and has many practical applications. Samples
generated by existing techniques for saliency detection cannot handle the noise
perturbations smoothly and fail to delineate the salient objects present in the
given scene. In this paper, we present a novel end-to-end coupled Denoising
based Saliency Prediction with Generative Adversarial Network (DSAL-GAN)
framework to address the problem of salient object detection in noisy images.
DSAL-GAN consists of two generative adversarial-networks (GAN) trained
end-to-end to perform denoising and saliency prediction altogether in a
holistic manner. The first GAN consists of a generator which denoises the noisy
input image, and in the discriminator counterpart we check whether the output
is a denoised image or ground truth original image. The second GAN predicts the
saliency maps from raw pixels of the input denoised image using a data-driven
metric based on saliency prediction method with adversarial loss. Cycle
consistency loss is also incorporated to further improve salient region
prediction. We demonstrate with comprehensive evaluation that the proposed
framework outperforms several baseline saliency models on various performance
benchmarks.