CoChat

R³Net: Recurrent Residual Refinement Network for Saliency Detection

Open access
Deng, Zijun, Hu, Xiaowei, Zhu, Lei, Xu, Xuemiao, Qin, Jing, Han, Guoqiang, Heng, Pheng-Ann · 2018 · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

Saliency detection is a fundamental yet challenging task in computer vision, aiming at highlighting the most visually distinctive objects in an image. We propose a novel recurrent residual refinement network (R^3Net) equipped with residual refinement blocks (RRBs) to more accurately detect salient regions of an input image. Our RRBs learn the residual between the intermediate saliency prediction and the ground truth by alternatively leveraging the low-level integrated features and the high-level integrated features of a fully convolutional network (FCN). While the low-level integrated features are capable of capturing more saliency details, the high-level integrated features can reduce non-salient regions in the intermediate prediction. Furthermore, the RRBs can obtain complementary saliency information of the intermediate prediction, and add the residual into the intermediate prediction to refine the saliency maps. We evaluate the proposed R^3Net on five widely-used saliency detection benchmarks by comparing it with 16 state-of-the-art saliency detectors. Experimental results show that our network outperforms our competitors in all the benchmark datasets.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.24963/ijcai.2018/95

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 35 references

Research works printed but not linked: 2

  1. Gao Huang, Zhuang Liu, K.Q. Wein- berger, and L. van der Maaten. Densely connected con- volutional networks. In CVPR, 2017.
  2. Krähenbühl and Koltun, 2011] Philipp Krähenbühl and Vladlen Koltun. Efficient inference in fully connected crfs with gaussian edge potentials. In NIPS, 2011.

Cited by

Metadata

Authors
Deng, Z., Hu, X., Zhu, L., Xu, X., Qin, J., Han, G., & Heng, P.-A.
Affiliations
  • South China University of Technology (CN)
  • Chinese University of Hong Kong (HK)
  • Hong Kong Polytechnic University (HK)
Venue
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Published
2018-07
Pages
684-690
OpenAlex
W2807746031
Cited by
589
References
34
Citations by year
2026: 28 · 2025: 54 · 2024: 78 · 2023: 97 · 2022: 100 · 2021: 102 · 2020: 87 · 2019: 40 · 2018: 3
FWCI
15.87
Type
conference paper
Language
en
Open access
Locations
  • International Joint Conference on Artificial Intelligence (publishedVersion)
  • Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
Funders
  • National Natural Science Foundation of China (61772206, U1611461, 61472145)
  • Innovation and Technology Commission
  • Natural Science Foundation of Guangdong Province (2017A030311027, 61472145)
  • Chinese University of Hong Kong
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Media Technology › Advanced Image Fusion Techniques
Keywords
saliency detection, recurrent neural networks, fully convolutional network, saliency map refinement, low-level and high-level features, visual attention

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.