Saliency Unified: A Deep Architecture for simultaneous Eye Fixation Prediction and Salient Object Segmentation

Kruthiventi, Srinivas SS and Gudisa, Vennela and Dholakiya, Jaley H and Babu, RV (2016) Saliency Unified: A Deep Architecture for simultaneous Eye Fixation Prediction and Salient Object Segmentation. In: 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), JUN 26-JUL 01, 2016, Las Vegas, NV, pp. 5781-5790.

PDF 2016_Iee_Con_Com_Vis_Pat_Rec_5781.pdf - Published Version Restricted to Registered users only Download (429kB) | Request a copy

Abstract

Human eye fixations often correlate with locations of salient objects in the scene. However, only a handful of approaches have attempted to simultaneously address the related aspects of eye fixations and object saliency. In this work, we propose a deep convolutional neural network (CNN) capable of predicting eye fixations and segmenting salient objects in a unified framework. We design the initial network layers, shared between both the tasks, such that they capture the object level semantics and the global contextual aspects of saliency, while the deeper layers of the network address task specific aspects. In addition, our network captures saliency at multiple scales via inception-style convolution blocks. Our network shows a significant improvement over the current state-of-the-art for both eye fixation prediction and salient object segmentation across a number of challenging datasets.

Item Type:	Conference Proceedings
Series.:	IEEE Conference on Computer Vision and Pattern Recognition
Additional Information:	29th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, JUN 26-JUL 01, 2016
Department/Centre:	Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited:	03 Jun 2017 09:45
Last Modified:	25 Feb 2019 05:48
URI:	http://eprints.iisc.ac.in/id/eprint/57129

Actions (login required)

View Item