Search: onr:"swepub:oai:DiVA.org:liu-199152" >
Discriminative Co-S...
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
-
- Li, Long (author)
- Northwestern Polytech Univ, Canada
-
- Han, Junwei (author)
- Northwestern Polytech Univ, Canada
-
- Zhang, Ni (author)
- Northwestern Polytech Univ, Canada
-
show more...
-
- Liu, Nian (author)
- Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates
-
- Khan, Salman (author)
- Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates; Australian Natl Univ, Australia
-
- Cholakkal, Hisham (author)
- Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates
-
- Anwer, Rao Muhammad (author)
- Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates
-
- Khan, Fahad (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Mohamed Bin Zayed Univ Artificial Intelligence, U Arab Emirates
-
show less...
-
(creator_code:org_t)
- IEEE COMPUTER SOC, 2023
- 2023
- English.
-
In: 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR. - : IEEE COMPUTER SOC. - 9798350301298 - 9798350301304 ; , s. 7247-7256
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules. We also design a token-guided feature refinement module to enhance the discriminability of the segmentation features under the guidance of the learned tokens. We perform iterative mutual promotion for the segmentation feature extraction and token construction. Experimental results on three benchmark datasets demonstrate the effectiveness of our proposed method. The source code is available at: https://github.com/dragonlee258079/DMT.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database