# Is Depth Really Necessary for Salient Object Detection?

arXiv: https://arxiv.org/abs/2006.00269 · HTML: https://mlsanity.com/paper/2006.00269/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2020.

## Built on by (most cited first, 23 of 23)

- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [Source-free Depth for Object Pop-out](https://mlsanity.com/paper/2212.05370/) (2022)
- [RGB-D Saliency Detection via Cascaded Mutual Information Minimization](https://mlsanity.com/paper/2109.07246/) (2021)
- [TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network](https://mlsanity.com/paper/2108.03990/) (2021)
- [HiDAnet: RGB-D Salient Object Detection via Hierarchical Depth Awareness](https://mlsanity.com/paper/2301.07405/) (2023)
- [Fantastic Animals and Where to Find Them: Segment Any Marine Animal with Dual SAM](https://mlsanity.com/paper/2404.04996/) (2024)
- [Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2108.05076/) (2021)
- [Towards Diverse Binary Segmentation via A Simple yet General Gated Network](https://mlsanity.com/paper/2303.10396/) (2023)
- [RGB-D Salient Object Detection with Ubiquitous Target Awareness](https://mlsanity.com/paper/2109.03425/) (2021)
- [Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction](https://mlsanity.com/paper/2203.04895/) (2022)
- [Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection](https://mlsanity.com/paper/2205.07179/) (2022)
- [Robust RGB-D Fusion for Saliency Detection](https://mlsanity.com/paper/2208.01762/) (2022)
- [Object Segmentation by Mining Cross-Modal Semantics](https://mlsanity.com/paper/2305.10469/) (2023)
- [Modality-Guided Subnetwork for Salient Object Detection](https://mlsanity.com/paper/2110.04904/) (2021)
- [Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation](https://mlsanity.com/paper/2303.10383/) (2023)
- [DFTR: Depth-supervised Fusion Transformer for Salient Object Detection](https://mlsanity.com/paper/2203.06429/) (2022)
- [Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff](https://mlsanity.com/paper/2301.06679/) (2023)
- [Distortion-aware Transformer in 360deg Salient Object Detection](https://mlsanity.com/paper/2308.03359/) (2023)
- [Pyramidal Attention for Saliency Detection](https://mlsanity.com/paper/2204.06788/) (2022)
- [GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm](https://mlsanity.com/paper/2508.07585/) (2025)
- [PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network](https://mlsanity.com/paper/2408.01137/) (2024)
- [Learning Spatially Adaptive Structural Coordination for Underwater Salient Object Detection](https://mlsanity.com/paper/2605.15535/) (2026)

## Abstract (arXiv)

Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. Most of the existing methods mainly rely on the RGB information to distinguish the salient objects, which faces difficulties in some complex scenarios. To solve this, many recent RGBD-based networks are proposed by adopting the depth map as an independent input and fuse the features with RGB information. Taking the advantages of RGB and RGBD methods, we propose a novel depth-aware salient object detection framework, which has following superior designs: 1) It only takes the depth information as training data while only relies on RGB information in the testing phase. 2) It comprehensively optimizes SOD features with multi-level depth-aware regularizations. 3) The depth information also serves as error-weighted map to correct the segmentation process. With these insightful designs combined, we make the first attempt in realizing an unified depth-aware framework with only RGB information as input for inference, which not only surpasses the state-of-the-art performances on five public RGB SOD benchmarks, but also surpasses the RGBD-based methods on five benchmarks by a large margin, while adopting less information and implementation light-weighted. The code and model will be publicly available.