AI Paper Atlas

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

AAAI 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 31 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Add LeNo to GateNetGateNet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM)FβMixed
Add LeNo to PiCANetPiCANet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM)FβImproved
Add LeNo to PFSNetPFSNet · RGB SOD adversarial benchmarks (PGD, ROSA, and FGSM)FβMixed
Add LeNo to GateNetGateNet · RGB clean benchmarksFβHurt
Add shallow noise (ablation)BBSNet · DUTS-D cleanFβ: .8117 -> .7594Hurt
Add shallow noise (ablation)BBSNet · DUTS-D-advFβ: .2473 -> .5197Improved
Add noise estimation after shallow noise (ablation)BBSNet with shallow noise · DUTS-D cleanFβ: .7594 -> .7852Improved
Add noise estimation after shallow noise (ablation)BBSNet with shallow noise · DUTS-D-advFβ: .5197 -> .5125No clear effect
Initialize noise with Gaussian rather than uniform or constant values (ablation)LeNo · Adversarial SOD datasetsFβImproved
Use more noise layers, extending them through stage2 (ablation)LeNo · NJU2K-advFβ: .7677 -> .7521Hurt
Use more noise layers, extending them through stage2 (ablation)LeNo · RGB and RGB-D clean and adversarial benchmarksFβHurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy