# MobileSal: Extremely Efficient RGB-D Salient Object Detection

arXiv: https://arxiv.org/abs/2012.13095 · HTML: https://mlsanity.com/paper/2012.13095/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2020.

## Built on by (most cited first, 25 of 25)

- [P2T: Pyramid Pooling Transformer for Scene Understanding](https://mlsanity.com/paper/2106.12011/) (2021)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network](https://mlsanity.com/paper/2108.03990/) (2021)
- [Learning Adaptive Fusion Bank for Multi-modal Salient Object Detection](https://mlsanity.com/paper/2406.01127/) (2024)
- [Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment](https://mlsanity.com/paper/2301.02778/) (2023)
- [StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2212.00937/) (2022)
- [Robust RGB-D Fusion for Saliency Detection](https://mlsanity.com/paper/2208.01762/) (2022)
- [CalibNet: Dual-branch Cross-modal Calibration for RGB-D Salient Instance Segmentation](https://mlsanity.com/paper/2307.08098/) (2023)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Unified-modal Salient Object Detection via Adaptive Prompt Learning](https://mlsanity.com/paper/2311.16835/) (2023)
- [Salient Object Detection in RGB-D Videos](https://mlsanity.com/paper/2310.15482/) (2023)
- [Adapting Segment Anything Model to Multi-modal Salient Object Detection with Semantic Feature Fusion Guidance](https://mlsanity.com/paper/2408.15063/) (2024)
- [MambaSOD: Dual Mamba-Driven Cross-Modal Fusion Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2410.15015/) (2024)
- [Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective](https://mlsanity.com/paper/2505.04758/) (2025)
- [Middle-level Fusion for Lightweight RGB-D Salient Object Detection](https://mlsanity.com/paper/2104.11543/) (2021)
- [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)
- [BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues](https://mlsanity.com/paper/2403.06600/) (2024)
- [StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2503.06601/) (2025)
- [Salient Object Detection From Arbitrary Modalities](https://mlsanity.com/paper/2405.03352/) (2024)
- [A Saliency Enhanced Feature Fusion based multiscale RGB-D Salient Object Detection Network](https://mlsanity.com/paper/2401.11914/) (2024)
- [GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm](https://mlsanity.com/paper/2508.07585/) (2025)
- [Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection](https://mlsanity.com/paper/2208.03918/) (2022)
- [HODINet: High-Order Discrepant Interaction Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2307.00954/) (2023)

## Abstract (arXiv)

The high computational cost of neural networks has prevented recent successes in RGB-D salient object detection (SOD) from benefiting real-world applications. Hence, this paper introduces a novel network, MobileSal, which focuses on efficient RGB-D SOD using mobile networks for deep feature extraction. However, mobile networks are less powerful in feature representation than cumbersome networks. To this end, we observe that the depth information of color images can strengthen the feature representation related to SOD if leveraged properly. Therefore, we propose an implicit depth restoration (IDR) technique to strengthen the mobile networks' feature representation capability for RGB-D SOD. IDR is only adopted in the training phase and is omitted during testing, so it is computationally free. Besides, we propose compact pyramid refinement (CPR) for efficient multi-level feature aggregation to derive salient objects with clear boundaries. With IDR and CPR incorporated, MobileSal performs favorably against state-of-the-art methods on six challenging RGB-D SOD datasets with much faster speed (450fps for the input size of 320 × 320) and fewer parameters (6.5M). The code is released at https://mmcheng.net/mobilesal.