Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

by   Shuhan Chen, et al.

In this paper, we aim to develop an efficient and compact deep network for RGB-D salient object detection, where the depth image provides complementary information to boost performance in complex scenarios. Starting from a coarse initial prediction by a multi-scale residual block, we propose a progressively guided alternate refinement network to refine it. Instead of using ImageNet pre-trained backbone network, we first construct a lightweight depth stream by learning from scratch, which can extract complementary features more efficiently with less redundancy. Then, different from the existing fusion based methods, RGB and depth features are fed into proposed guided residual (GR) blocks alternately to reduce their mutual degradation. By assigning progressive guidance in the stacked GR blocks within each side-output, the false detection and missing parts can be well remedied. Extensive experiments on seven benchmark datasets demonstrate that our model outperforms existing state-of-the-art approaches by a large margin, and also shows superiority in efficiency (71 FPS) and model size (64.9 MB).



There are no comments yet.


page 3

page 4

page 9

page 10

page 11

page 15

page 16

page 18


Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection

Salient object detection(SOD) aims at locating the most significant obje...

PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detection

Fully convolutional neural networks (FCNs) have shown outstanding perfor...

A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection

Existing RGB-D salient object detection (SOD) approaches concentrate on ...

Reverse Attention for Salient Object Detection

Benefit from the quick development of deep learning techniques, salient ...

Boundary-Aware Salient Object Detection via Recurrent Two-Stream Guided Refinement Network

Recent deep learning based salient object detection methods which utiliz...

Depth Quality Aware Salient Object Detection

The existing fusion based RGB-D salient object detection methods usually...

(DE)^2 CO: Deep Depth Colorization

Object recognition on depth images using convolutional neural networks r...

Code Repositories


Code for the ECCV 2020 paper: Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.