MTFNet: Mutual-Transformer Fusion Network for RGB-D Salient Object Detection
release_bzg5kd6wlvhsjbo67ci7fx3jqy
by
Xixi Wang, Bo Jiang, Xiao Wang, Bin Luo
2021
Abstract
Salient object detection (SOD) on RGB-D images is an active problem in
computer vision. The main challenges for RGB-D SOD problem are how to 1)
extract the accurate features for RGB and Depth image data with clutter
background or poor image quality and 2) explore the complementary information
between RGB and Depth image data. To address these challenges, we propose a
novel Mutual-Transformer Fusion Network (MTFNet) for RGB-D SOD. MTFNet contains
two main modules, i.e., Focal Feature Extractor (FFE) and Mutual-Transformer
Fusion (MTF). FFE aims to extract the more accurate CNN features for RGB and
Depth images by introducing a novel pixel-level focal regularization to guide
CNN feature extractor. MTF is designed to deeply exploit the multi-modal
interaction between RGB and Depth images on both coarse and fine scales. The
main benefit of MTF is that it conducts the learning of intra-modality and
inter-modality simultaneously and thus can achieve communication across
different modalities more directly and sufficiently. Comprehensive experimental
results on six public benchmarks demonstrate the superiority of our proposed
MTFNet.
In text/plain
format
Archived Files and Locations
application/pdf 2.4 MB
file_agwi3iwgsjbetmw3esjeyswjxy
|
arxiv.org (repository) web.archive.org (webarchive) |
2112.01177v1
access all versions, variants, and formats of this works (eg, pre-prints)