Research map / Adversarial robustness and security / Attacks on text and graphs
LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise
He Wang, Lin Wan, He Tang
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 LeNo to GateNet | GateNet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM) | Fβ | Mixed |
| Add LeNo to PiCANet | PiCANet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM) | Fβ | Improved |
| Add LeNo to PFSNet | PFSNet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM) | Fβ | Mixed |
| Add LeNo to GateNet | GateNet · RGB clean benchmarks | Fβ | Hurt |
| Add shallow noise (ablation) | BBSNet · DUTS-D clean | Fβ: .8117 -> .7594 | Hurt |
| Add shallow noise (ablation) | BBSNet · DUTS-D-adv | Fβ: .2473 -> .5197 | Improved |
| Add noise estimation after shallow noise (ablation) | BBSNet with shallow noise · DUTS-D clean | Fβ: .7594 -> .7852 | Improved |
| Add noise estimation after shallow noise (ablation) | BBSNet with shallow noise · DUTS-D-adv | Fβ: .5197 -> .5125 | No clear effect |
| Initialize noise with Gaussian rather than uniform or constant values (ablation) | LeNo · Adversarial SOD datasets | Fβ | Improved |
| Use more noise layers, extending them through stage2 (ablation) | LeNo · NJU2K-adv | Fβ: .7677 -> .7521 | Hurt |
| Use more noise layers, extending them through stage2 (ablation) | LeNo · RGB and RGB-D clean and adversarial benchmarks | Fβ | Hurt |
Closest papers by meaning
- Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning (AAAI 2022 · similarity 0.86)
- Salient Object Detection in the Deep Learning Era: An In-Depth Survey (TPAMI 2021 · similarity 0.86)
- Uncertainty-Aware Joint Salient Object and Camouflaged Object Detection (CVPR 2021 · similarity 0.86)
- Specificity-Preserving RGB-D Saliency Detection (ICCV 2021 · similarity 0.86)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.86)
- Disentangled High Quality Salient Object Detection (ICCV 2021 · 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.
