Research map / Detection and segmentation / CNN features
IPDiff: Diffusion-driven ORSI Salient Object Detection with Information Reconstruction and Multi-Prior Guidance
Gongyang Li, Zhen Bai, Runmin Cong, Dan Zeng, Weisi Lin, Xiao-Ping Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spectral information reconstruction (spectrum decoupling, weighting, aggregation) to attention (ablation) | IPDiff · EORSSD | S-measure: .9375 -> .9461 | Improved |
| add spectrum decoupling before weighting instead of direct reconstruction (ablation) | IPDiff · EORSSD | S-measure: .9448 -> .9461 | Improved |
| use adaptive hyperparameters instead of fixed for decoupling and aggregation (ablation) | IPDiff · EORSSD | S-measure: .9453 -> .9461 | Improved |
| add the saliency prior (ablation) | IPDiff · EORSSD | max F-measure: .8935 -> .9033 | Improved |
| inject hierarchical priors instead of an integrated prior (ablation) | IPDiff · EORSSD | max F-measure: .8936 -> .9033 | Improved |
| add IPM information perturbation during training (ablation) | IPDiff · EORSSD | max E-measure: .9811 -> .9861 | Improved |
| add information transmission from encoder to decoder (ablation) | IPDiff · EORSSD | max F-measure: .8915 -> .9033 | Improved |
| increase perturbation rate from 20% to 60% (ablation) | IPDiff · EORSSD | max F-measure: .9033 -> .8974 | Hurt |
| use perturbation rate 20% instead of 0% (ablation) | IPDiff · EORSSD | max F-measure: .8994 -> .9033 | Improved |
| increase number of IPMs from 0 to 4 (ablation) | IPDiff · EORSSD | MAE: .0050 -> .0044 | Improved |
| add edge loss to the basic spatial loss (ablation) | IPDiff · EORSSD | MAE: .0066 -> .0044 | Improved |
| add spectral domain loss to the spatial loss (ablation) | IPDiff · EORSSD | max F-measure: .8964 -> .9033 | Improved |
Closest papers by meaning
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.88)
- Breaking Barriers, Localizing Saliency: A Large-Scale Benchmark and Baseline for Condition-Constrained Salient Object Detection (TPAMI 2025 · similarity 0.88)
- SimpleDiffusion: A Lightweight and Efficient Conditional Diffusion Model for Multi-Modal Salient Object Detection (AAAI 2026 · similarity 0.87)
- SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening (NeurIPS 2024 · similarity 0.86)
- Conditional Diffusion Models for Camouflaged and Salient Object Detection (TPAMI 2025 · similarity 0.86)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
