Existing CNNs-Based RGB-D salient object detection (SOD) networks are all
required to be pretrained on the ImageNet to learn the hierarchy features which
helps provide a good initialization. However, the collection and annotation of
large-scale datasets are time-consuming and expensive. In this paper, we
utilize self-supervised representation learning (SSL) to design two pretext
tasks: the cross-modal auto-encoder and the depth-contour estimation. Our
pretext tasks require only a few and unlabeled RGB-D datasets to perform
pretraining, which makes the network capture rich semantic contexts and reduce
the gap between two modalities, thereby providing an effective initialization
for the downstream task. In addition, for the inherent problem of cross-modal
fusion in RGB-D SOD, we propose a consistency-difference aggregation (CDA)
module that splits a single feature fusion into multi-path fusion to achieve an
adequate perception of consistent and differential information. The CDA module
is general and suitable for cross-modal and cross-level feature fusion.
Extensive experiments on six benchmark datasets show that our self-supervised
pretrained model performs favorably against most state-of-the-art methods
pretrained on ImageNet. The source code will be publicly available at
\textcolor{red}{https://github.com/Xiaoqi-Zhao-DLUT/SSLSOD}.

本文通过使用自监督表示学习方法，在只有少量无标签 RGB-D 数据集的情况下，利用两个预处理任务（跨模态自编码器和深度轮廓估计）对 CNNs-Based RGB-D 显着物体检测网络进行预训练，建立一个富有语义上下文的网络初始化，同时提出了一种一致性 - 差异性聚合模块（CDA）来解决 RGB-D SOD 中的跨模态融合问题。实验结果表明，本文的自监督预训练模型表现优于那些在 ImageNet 上进行预训练的最先进方法。