Middle-level Fusion for Lightweight RGB-D Salient Object Detection

TL;DR

This paper introduces a lightweight RGB-D salient object detection model using middle-level fusion, effectively capturing cross-modal information while significantly reducing parameters and maintaining high speed.

Contribution

The paper proposes a novel middle-level fusion structure for RGB-D SOD, improving cross-modal feature exploitation and reducing model complexity compared to existing methods.

Findings

Model contains only 3.9M parameters.

Runs at 33 FPS, enabling real-time applications.

Outperforms state-of-the-art methods on benchmark datasets.

Abstract

Most existing lightweight RGB-D salient object detection (SOD) models are based on two-stream structure or single-stream structure. The former one first uses two sub-networks to extract unimodal features from RGB and depth images, respectively, and then fuses them for SOD. While, the latter one directly extracts multi-modal features from the input RGB-D images and then focuses on exploiting cross-level complementary information. However, two-stream structure based models inevitably require more parameters and single-stream structure based ones cannot well exploit the cross-modal complementary information since they ignore the modality difference. To address these issues, we propose to employ the middle-level fusion structure for designing lightweight RGB-D SOD model in this paper, which first employs two sub-networks to extract low- and middle-level unimodal features, respectively, and then fuses those extracted middle-level unimodal features for extracting corresponding high-level multi-modal features in the subsequent sub-network. Different from existing models, this structure can effectively exploit the cross-modal complementary information and significantly reduce the network's parameters, simultaneously. Therefore, a novel lightweight SOD model is designed, which contains a information-aware multi-modal feature fusion (IMFF) module for effectively capturing the cross-modal complementary information and a lightweight feature-level and decision-level feature fusion (LFDF) module for aggregating the feature-level and the decision-level saliency information in different stages with less parameters. Our proposed model has only 3.9M parameters and runs at 33 FPS. The experimental results on several benchmark datasets verify the effectiveness and superiority of the proposed method over some state-of-the-art methods.