# CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse

arXiv: https://arxiv.org/abs/1909.09309 · HTML: https://mlsanity.com/paper/1909.09309/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection](https://mlsanity.com/paper/2405.09782/) (2024)
- [LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise](https://mlsanity.com/paper/2210.15392/) (2022)
- [Dual Swin-Transformer based Mutual Interactive Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2206.03105/) (2022)
- [Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection](https://mlsanity.com/paper/2208.03918/) (2022)
- [Hierarchical Cross-modal Transformer for RGB-D Salient Object Detection](https://mlsanity.com/paper/2302.08052/) (2023)
- [Dissecting RGB-D Learning for Improved Multi-modal Fusion](https://mlsanity.com/paper/2308.10019/) (2023)
- [Robust Salient Object Detection on Compressed Images Using Convolutional Neural Networks](https://mlsanity.com/paper/2409.13464/) (2024)
- [Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approach](https://mlsanity.com/paper/2509.15573/) (2025)

## Abstract (arXiv)

The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection and cross-modal complement fusion. To learn discriminative modal-specific features, we propose a hierarchical cross-modal distillation scheme, in which the well-learned source modality provides supervisory signals to facilitate the learning process for the new modality. To better extract the complementary cues, we formulate a residual function to incorporate complements from the paired modality adaptively. Furthermore, a top-down fusion structure is constructed for sufficient cross-modal interactions and cross-level transmissions. The experimental results demonstrate the effectiveness of the proposed cross-modal distillation scheme in zero-shot saliency detection and pre-training on a new modality, as well as the advantages in selecting and fusing cross-modal/cross-level complements.