Sorry, you need to enable JavaScript to visit this website.

A SALIENCY ENHANCED FEATURE FUSION BASED MULTISCALE RGB-D SALIENT OBJECT DETECTION NETWORK

DOI:
10.60864/7ffg-bv55
Citation Author(s):
Submitted by:
Qingyi Zhao
Last updated:
6 June 2024 - 10:50am
Document Type:
Poster
Document Year:
2024
Event:
Presenters:
Qingyi Zhao
Paper Code:
SPTM-P4.2
 

Multiscale convolutional neural network (CNN) has demonstrated remarkable capabilities in solving various vision problems. However, fusing features of different scales always results in large model sizes, impeding the application of mul-
tiscale CNNs in RGB-D saliency detection. In this paper, we propose a customized feature fusion module, called Saliency Enhanced Feature Fusion (SEFF), for RGB-D saliency detection. SEFF utilizes saliency maps of the neighboring scales
to enhance the necessary features for fusing, resulting in more representative fused features. Our multiscale RGB-D saliency detector uses SEFF and processes images with three different scales. SEFF is used to fuse the features of RGB and depth images, as well as the features of decoders at different scales. Extensive experiments on five benchmark datasets have demonstrated the superiority of our method over ten SOTA saliency detectors

up
0 users have voted:

Comments

RGB-D, saliency detection, salient object detection, multiscale, feature fusion