Research map / Detection and segmentation / CNN features
RGB-D salient object detection
Use depth cues with attention and distillation for salient object detection.
47 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in CNN features, keyword cluster “salient · saliency · sod”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
8 papers in 2023–24 and 16 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 2.4% to 4.6%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Real-Time Salient Object Detection With a Minimum Spanning Tree (CVPR 2016 · 301 citations)
- 2017 · What Is and What Is Not a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors (CVPR 2017 · 93 citations)
- 2018 · Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (CVPR 2018 · 366 citations)
- 2019 · A Simple Pooling-Based Design for Real-Time Salient Object Detection (CVPR 2019 · 1,150 citations)
- 2020 · JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (CVPR 2020 · 366 citations)
- 2021 · Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection (CVPR 2021 · 287 citations)
- 2022 · Self-Supervised Pretraining for RGB-D Salient Object Detection (AAAI 2022 · 74 citations)
- 2023 · High-Resolution Iterative Feedback Network for Camouflaged Object Detection (AAAI 2023 · 213 citations)
- 2024 · DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation (ICLR 2024 · 16 citations)
- 2025 · Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · 15 citations)
- 2026 · Breaking Alignment Barriers: TPS-Driven Semantic Correlation Learning for Alignment-Free RGB-T Salient Object Detection (AAAI 2026 · 2 citations)
Earliest papers here
- Real-Time Salient Object Detection With a Minimum Spanning Tree (CVPR 2016 · 301 citations)
- Local Background Enclosure for RGB-D Salient Object Detection (CVPR 2016 · 231 citations)
- Unconstrained Salient Object Detection via Proposal Subset Optimization (CVPR 2016 · 109 citations)
What has been tried
36 papers here report 396 measured changes (a component added, removed or swapped, compared with a baseline): helped 76%, no clear effect 3%, hurt 20%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Pretrain with RGB-depth pairs instead of replacing depth maps with RGB images | NYU DepthV2 · mIoU | 53.3 -> 55.6 | Helped | DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation (ICLR 2024 · 16 citations) |
| add SGMB | DUTS · Fm | 0.916 -> 0.930 | Helped | Samba: A Unified Mamba-based Framework for General Salient Object Detection (CVPR 2025 · 15 citations) |
| Add iterative mask refinement (IMR) | UIEB · PSNR | 22.864 -> 24.938 | Helped | WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration (AAAI 2025 · 14 citations) |
| Add the bit-plane slicing (BS) block | VT5000 · F-measure | 0.708 -> 0.848 | Helped | SMR-Net: Semantic-Guided Mutually Reinforcing Network for Cross-Modal Image Fusion and Salient Object Detection (AAAI 2025 · 12 citations) |
| Use PVT with multi-scale attention feature fusion instead of the native SD VAE as the global feature extractor | DUTS-TE, NJUD, and VT1000 · Fβ | 5.33% | Helped | DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · 5 citations) |
| Replace the transformer decoder layer with the fovea layer | ASSR · SA-SOR | 0.672 -> 0.685 | Helped | SeqRank: Sequential Ranking of Salient Objects (AAAI 2024 · 5 citations) |
| use α=0, excluding the background frame from the loss | MSOD and DUTS · foreground-frame score | Mixed | Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection (ICML 2024 · 1 citation) | |
| Add GTPD to the HRNet with HAR | HSOD-BIT-V2 · AUC | 0.883 -> 0.988 | Helped | HSOD-BIT-V2: A Challenging Benchmark for Hyperspectral Salient Object Detection (AAAI 2025 · 0 citations) |
| add the succession-stage high-resolution refinement to LrLM | HRSOD-TE · MAEBD | 0.206 -> 0.166 | Helped | ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection (ICML 2024) |
What reviewers will expect
Datasets and baselines named in the 6 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- VT5000 · 3 of 6 papers
- NJUD · 2 of 6 papers
- NLPR · 2 of 6 papers
Baselines
- U2Net · 3 of 6 papers
- VST · 2 of 6 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 24 papers; from OpenAlex and the papers' affiliations).
- ETH Zurich · 2 papers
- Sun Yat-sen University · 2 papers
- Mohamed bin Zayed University of Artificial Intelligence · 2 papers
- Chinese Academy of Sciences · 2 papers
- Shandong University · 2 papers
Use it
Download BibTeX of 40 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- RGB salient object detection (61 papers)
Elsewhere in the topic
- Context modeling for semantic segmentation (241 papers)
- Region-based and query-based detectors (183 papers)
- Local features and context in CNNs (170 papers)
- Context for hard detection conditions (133 papers)
- Domain-specific segmentation and detection (118 papers)
- Convolution-transformer backbones (101 papers)
- Box regression and loss design (94 papers)
- Efficient DETR query design (85 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).