JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection

TL;DR

This paper introduces JL-DCF, a novel RGB-D salient object detection framework that jointly learns from both modalities using a Siamese network and employs densely-cooperative fusion for improved feature integration, demonstrating superior performance across multiple datasets.

Contribution

The paper presents a joint learning and densely-cooperative fusion architecture that effectively combines RGB and depth information for salient object detection, improving over existing models.

Findings

Achieves ~1.9% higher S-measure than top-1 D3Net model on six datasets.

Demonstrates strong generalization across diverse challenging datasets.

Provides a potential solution for real-world RGB-D saliency detection applications.

Abstract

This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection. Existing models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately-designed training process. In contrast, our JL-DCF learns from both RGB and depth inputs through a Siamese network. To this end, we propose two effective components: joint learning (JL), and densely-cooperative fusion (DCF). The JL module provides robust saliency feature learning, while the latter is introduced for complementary feature discovery. Comprehensive experiments on four popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the top-1 D3Net model by an average of ~1.9% (S-measure) across six challenging datasets, showing that the proposed framework offers a potential solution for real-world applications and could provide more insight into the cross-modality complementarity task. The code will be available at https://github.com/kerenfu/JLDCF/.