• Home
  • Search
  • ELD-Net: An Efficient Deep Learning Architecture for Accurate Saliency Detection.
  • Cite Icon48
  • https://doi.org/10.1109/tpami.2017.2737631Copy DOI Icon

ELD-Net: An Efficient Deep Learning Architecture for Accurate Saliency Detection.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recent advances in saliency detection have utilized deep learning to obtain high-level features to detect salient regions in scenes. These advances have yielded results superior to those reported in past work, which involved the use of hand-crafted low-level features for saliency detection. In this paper, we propose ELD-Net, a unified deep learning framework for accurate and efficient saliency detection. We show that hand-crafted features can provide complementary information to enhance saliency detection that uses only high-level features. Our method uses both low-level and high-level features for saliency detection. High-level features are extracted using GoogLeNet, and low-level features evaluate the relative importance of a local region using its differences from other regions in an image. The two feature maps are independently encoded by the convolutional and the ReLU layers. The encoded low-level and high-level features are then combined by concatenation and convolution. Finally, a linear fully connected layer is used to evaluate the saliency of a queried region. A full resolution saliency map is obtained by querying the saliency of each local region of an image. Since the high-level features are encoded at low resolution, and the encoded high-level features can be reused for every query region, our ELD-Net is very fast. Our experiments show that our method outperforms state-of-the-art deep learning-based saliency detection methods.

Similar Papers
  • Conference Article
  • Citations576

Deep Saliency with Encoded Low Level Distance Map and High Level Features

  • Jun 01, 2016
  • Gayoung Lee +2
  • Research Article
  • Citations8

Saliency detection via integrating deep learning architecture and low-level features

  • Apr 27, 2019
  • Neurocomputing
  • Jianning Chi +4
  • Research Article

A Saliency Detection Model via Fusing Extracted Low-level and High-level Features from an Image

  • Dec 03, 2018
  • SHILAP Revista de lepidopterología
  • S Asadi Amiri +1
  • Research Article
  • Citations12

Content Based Image Retrieval

  • Jan 01, 2013
  • IOSR Journal of Computer Engineering
  • Showkat Dar
  • Research Article
  • Citations12

Exploring spatiotemporal neural dynamics of the human visual cortex.

  • Jun 23, 2019
  • Human Brain Mapping
  • Ying Yang +3
  • PDF
  • Research Article
  • Citations75

Image Feature Types and Their Predictions of Aesthetic Preference and Naturalness.

  • Apr 28, 2017
  • Frontiers in Psychology
  • Frank F Ibarra +5
  • Conference Article
  • Citations8

An image retrieval technique based on texture features using semantic properties

  • Feb 01, 2013
  • K.P Jisha +2
  • Supplementary Content
  • Citations76

Improved Deep Learning Network Based in combination with Cost-sensitive Learning for Early Detection of Ovarian Cancer in Color Ultrasound Detecting System.

  • Jun 28, 2019
  • Journal of Medical Systems
  • Lei Zhang +2
  • PDF
  • Research Article
  • Citations4

Saliency Detection Based on Low-Level and High-Level Features via Manifold-Space Ranking

  • Jan 15, 2023
  • Electronics
  • Xiaoli Li +2
  • Research Article
  • Citations244

Content-Based Brain Tumor Retrieval for MR Images Using Transfer Learning

  • Jan 01, 2019
  • IEEE Access
  • Zar Nawab Khan Swati +6
  • Research Article
  • Citations27

Non-manual grammatical marker recognition based on multi-scale, spatio-temporal analysis of head pose and facial expressions

  • Mar 11, 2014
  • Image and Vision Computing
  • Jingjing Liu +6
  • Research Article
  • Citations29

A scheme for high level data classification using random walk and network measures

  • Sep 15, 2017
  • Expert Systems with Applications
  • Thiago Henrique Cupertino +4
  • Conference Article
  • Citations4

Robust pedestrian detection using low level and high level features

  • May 01, 2013
  • Fariba Takarli +2
  • Research Article

Diagnosis of Chronic Brain Syndrome Using Deep Learning

  • Feb 28, 2023
  • International Journal for Research in Applied Science and Engineering Technology
  • Pentyala Srija +2
  • Book Chapter
  • Citations12

Extended Non-local Feature for Visual Saliency Detection in Low Contrast Images

  • Jan 01, 2019
  • Xin Xu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.