DSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks
This addresses a challenge in computer vision for applications requiring robust saliency detection under noise, but it appears incremental as it combines existing techniques like GANs and cycle consistency loss.
The paper tackles the problem of salient object detection in noisy images by proposing DSAL-GAN, a coupled framework that integrates denoising and saliency prediction using two GANs, and it outperforms baseline models on various benchmarks.
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.