Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration

TL;DR

This paper introduces CAAI-Net, a novel RGB-D saliency detection model that employs complementary attention and adaptive feature fusion, significantly improving accuracy by effectively integrating RGB and depth information.

Contribution

The paper proposes a unified framework with novel CCA and AFI modules for enhanced RGB-D saliency detection, addressing depth map quality issues and improving feature integration.

Findings

Outperforms nine state-of-the-art models on six benchmark datasets

Effective suppression of background disturbances in salient object detection

Demonstrates the effectiveness of proposed CCA and AFI modules through ablation studies

Abstract

Saliency detection based on the complementary information from RGB images and depth maps has recently gained great popularity. In this paper, we propose Complementary Attention and Adaptive Integration Network (CAAI-Net), a novel RGB-D saliency detection model that integrates complementary attention based feature concentration and adaptive cross-modal feature fusion into a unified framework for accurate saliency detection. Specifically, we propose a context-aware complementary attention (CCA) module, which consists of a feature interaction component, a complementary attention component, and a global-context component. The CCA module first utilizes the feature interaction component to extract rich local context features. The resulting features are then fed into the complementary attention component, which employs the complementary attention generated from adjacent levels to guide the attention at the current layer so that the mutual background disturbances are suppressed and the network focuses more on the areas with salient objects. Finally, we utilize a specially-designed adaptive feature integration (AFI) module, which sufficiently considers the low-quality issue of depth maps, to aggregate the RGB and depth features in an adaptive manner. Extensive experiments on six challenging benchmark datasets demonstrate that CAAI-Net is an effective saliency detection model and outperforms nine state-of-the-art models in terms of four widely-used metrics. In addition, extensive ablation studies confirm the effectiveness of the proposed CCA and AFI modules.