Pyramidal Attention for Saliency Detection

T. Hussain, Saeed Anwar, S. Anwar, L. Petersson, S. Wook Baik

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)peer-review

17 Citations (Scopus)


Salient object detection (SOD) extracts meaningful contents from an input image. RGB-based SOD methods lack the complementary depth clues; hence, providing limited performance for complex scenarios. Similarly, RGB-D models process RGB and depth inputs, but the depth data availability during testing may hinder the model's practical applicability. This paper exploits only RGB images, estimates depth from RGB, and leverages the intermediate depth features. We employ a pyramidal attention structure to extract multi-level convolutional-transformer features to process initial stage representations and further enhance the subsequent ones. At each stage, the backbone transformer model produces global receptive fields and computing in parallel to attain fine-grained global predictions refined by our residual convolutional attention decoder for optimal saliency prediction. We report significantly improved performance against 21 and 40 state-of-the-art SOD methods on eight RGB and RGB-D datasets, respectively. Consequently, we present a new SOD perspective of generating RGB-D SOD without acquiring depth data during training and testing and assist RGB methods with depth clues for improved performance. The code and trained models are available at

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022
Number of pages11
ISBN (Electronic)9781665487399
ISBN (Print)9781665487399
Publication statusPublished - 23 Aug 2022

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516


  • Computer


Dive into the research topics of 'Pyramidal Attention for Saliency Detection'. Together they form a unique fingerprint.

Cite this