scispace - formally typeset
Proceedings ArticleDOI

Deep Level Sets for Salient Object Detection

Reads0
Chats0
TLDR
This work proposes a deep Level Set network to produce compact and uniform saliency maps and drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.
Abstract
Deep learning has been applied to saliency detection in recent years. The superior performance has proved that deep networks can model the semantic properties of salient objects. Yet it is difficult for a deep network to discriminate pixels belonging to similar receptive fields around the object boundaries, thus deep networks may output maps with blurred saliency and inaccurate boundaries. To tackle such an issue, in this work, we propose a deep Level Set network to produce compact and uniform saliency maps. Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency. Besides, to propagate saliency information among pixels and recover full resolution saliency map, we extend a superpixel-based guided filter to be a layer in the network. The proposed network has a simple structure and is trained end-to-end. During testing, the network can produce saliency maps by efficiently feedforwarding testing images at a speed over 12FPS on GPUs. Evaluations on benchmark datasets show that the proposed method achieves state-of-the-art performance.

read more

Content maybe subject to copyright    Report

Citations
More filters
Proceedings ArticleDOI

BASNet: Boundary-Aware Salient Object Detection

TL;DR: Experimental results on six public datasets show that the proposed predict-refine architecture, BASNet, outperforms the state-of-the-art methods both in terms of regional and boundary evaluation measures.
Proceedings ArticleDOI

EGNet: Edge Guidance Network for Salient Object Detection

TL;DR: In this article, an edge guidance network (EGNet) is proposed for salient object detection with three steps to simultaneously model these two kinds of complementary information in a single network, which can help locate salient objects especially their boundaries more accurately.
Proceedings ArticleDOI

PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection

TL;DR: Zhang et al. as discussed by the authors proposed a pixel-wise contextual attention network to learn to selectively attend to informative context locations for each pixel, which can generate an attention map in which each attention weight corresponds to the contextual relevance at each context location.
Proceedings ArticleDOI

Salient Object Detection With Pyramid Attention and Salient Edges

TL;DR: Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection and the deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU).
Book ChapterDOI

Reverse Attention for Salient Object Detection

TL;DR: An accurate yet compact deep network for efficient salient object detection that employs residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy.
References
More filters
Proceedings ArticleDOI

Salient object detection via bootstrap learning

TL;DR: A bootstrap learning algorithm for salient object detection in which both weak and strong models are exploited and a strong classifier based on samples directly from an input image is learned to detect salient pixels.
Journal ArticleDOI

Saliency-Aware Video Compression

TL;DR: Experimental results indicate that the proposed saliency-aware video compression method is able to improve visual quality of encoded video relative to conventional rate distortion optimized video coding, as well as two state-of-the art perceptual video coding methods.
Journal ArticleDOI

SalientShape: group saliency in image collections

TL;DR: This work introduces group saliency to achieve superior unsupervised salient object segmentation by extracting salient objects (in collections of pre-filtered images) that maximize between-image similarities and within-image distinctness.
Proceedings ArticleDOI

Real-Time Salient Object Detection with a Minimum Spanning Tree

TL;DR: This paper proposes an exact and iteration free solution on a minimum spanning tree that largely reduces the search space of shortest paths, resulting an efficient and high quality distance transform algorithm and introduces a boundary dissimilarity measure to compliment the shortage of distance transform for salient object detection.
Proceedings ArticleDOI

Recurrent Attentional Networks for Saliency Detection

TL;DR: Zhang et al. as discussed by the authors proposed a recurrent attentional convolutional-deconvolutional network (RACDNN) which uses spatial transformer and recurrent network units to iteratively attend to selected image subregions to perform saliency refinement progressively.
Related Papers (5)