DISC: Deep Image Saliency Computing via Progressive Representation Learning

11/13/2015
by   Tianshui Chen, et al.
0

Salient object detection increasingly receives attention as an important component or step in several pattern recognition and image processing tasks. Although a variety of powerful saliency models have been intensively proposed, they usually involve heavy feature (or model) engineering based on priors (or assumptions) about the properties of objects and backgrounds. Inspired by the effectiveness of recently developed feature learning, we provide a novel Deep Image Saliency Computing (DISC) framework for fine-grained image saliency computing. In particular, we model the image saliency from both the coarse- and fine-level observations, and utilize the deep convolutional neural network (CNN) to learn the saliency representation in a progressive manner. Specifically, our saliency model is built upon two stacked CNNs. The first CNN generates a coarse-level saliency map by taking the overall image as the input, roughly identifying saliency regions in the global context. Furthermore, we integrate superpixel-based local context information in the first CNN to refine the coarse-level saliency map. Guided by the coarse saliency map, the second CNN focuses on the local context to produce fine-grained and accurate saliency map while preserving object details. For a testing image, the two CNNs collaboratively conduct the saliency computing in one shot. Our DISC framework is capable of uniformly highlighting the objects-of-interest from complex background while preserving well object details. Extensive experiments on several standard benchmarks suggest that DISC outperforms other state-of-the-art methods and it also generalizes well across datasets without additional training. The executable version of DISC is available online: http://vision.sysu.edu.cn/projects/DISC.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 9

page 11

page 12

page 13

research
07/12/2016

RGBD Salient Object Detection via Deep Fusion

Numerous efforts have been made to design different low level saliency c...
research
08/01/2018

Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data

This paper investigates the role of saliency to improve the classificati...
research
05/23/2017

Salient Object Detection with Semantic Priors

Salient object detection has increasingly become a popular topic in cogn...
research
09/08/2018

Video Smoke Detection Based on Deep Saliency Network

Video smoke detection is a promising fire detection method especially in...
research
10/18/2020

Unsupervised Foveal Vision Neural Networks with Top-Down Attention

Deep learning architectures are an extremely powerful tool for recognizi...
research
05/02/2022

Understanding CNNs from excitations

For instance-level explanation, in order to reveal the relations between...
research
03/01/2017

Saliency Detection by Forward and Backward Cues in Deep-CNNs

As prior knowledge of objects or object features helps us make relations...

Please sign up or login with your details

Forgot password? Click here to reset