Co-Detection in Images Using Saliency and Siamese Networks

Abstract

Co-Detection is an important problem in computer vision, which involves detecting common objects from multiple images. In this paper, we address the co-detection problem and propose an integrated deep learning model involving two networks for co-detection. Our proposed model detects the objects of individual images using a convolutional neural network by generating the saliency maps, which are passed as input in a Siamese neural network to ascertain whether the salient objects in both the images are similar or different. We have tested our model on the iCoseg dataset achieving high-quality results.