DISC: Deep Image Saliency Computing via Progressive Representation Learning

Abstract

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-theart 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.

Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining

“…A pioneer work was proposed by Zheng et al, [40], in which they proposed to represent public traffic trajectories as graphs or tensor structures. Inspired by the significant progress of deep learning on various tasks [5,17,18,37,38], many researchers also have attempted to handle this task with deep neural network. Fouladgar et al [9] introduced a scalable decentralized deep neural networks for urban short-term traffic congestion prediction.…”

Video smoke detection based on deep saliency network

“…There are many works using multiple branches for saliency detection. Chen [21] proposes a saliency model built upon two stacked CNNs. The first CNN generates a coarse-level saliency map in the global context.…”

Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition

“…However, these methods involve in heavy annotations of object parts, and moreover, manually defined parts may not be optimal for the final recognition. Instead, He et al [He and Peng, 2017a] adopt salient region localization techniques [Chen et al, 2016; to automatically generate bounding box annotations of the discriminative regions. Recently, visual attention models [Mnih et al, 2014;Chen et al, 2018;Liu et al, 2018] have been intensively proposed to automatically search the informative regions, and some works also apply this technique to fine-grained recognition task [Liu et al, 2016;Peng et al, 2018].…”