AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation

Hieu Le, Tomas F. Yago Vicente, Vu Nguyen, Minh Hoai, Dimitris Samaras

ECCV 2018 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 127 citations (OpenAlex)

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 changedWhereMeasuredEffect
add adversarially attenuated training images from A-Net (ablation)D-Net · SBU testBER: 8.8 -> 5.4Improved
add adversarially attenuated training images from A-Net (ablation)D-Net · UCF test (trained on SBU)BER: 11.8 -> 9.4Improved
add physics-based loss L_ph to A-Net (ablation)D-Net without lambda_adv · SBU testBER: 7.1 -> 5.7Improved
add physics-based loss L_ph to A-Net (ablation)D-Net without lambda_adv · UCF test (trained on SBU)BER: 13.6 -> 9.9Improved
add shadow-strength-based weight lambda_adv for adversarial examples (ablation)D-Net with L_ph · SBU testBER: 5.7 -> 5.4Improved
add shadow-strength-based weight lambda_adv for adversarial examples (ablation)D-Net with L_ph · UCF test (trained on SBU)BER: 9.9 -> 9.4Improved
increase adversarial loss weight lambda_sd from 1 to 10 (ablation)A-Net / D-Net · SBU testBER: 5.4 -> 6.5Hurt
rebalance real and adversarial weights to lambda_adv0=0.5 and lambda_real=0.5 (ablation)D-Net · SBU testBER: 5.4 -> 7.0Hurt
add D-Net with A-Net versus ST-CGAN (shadow error rate)D-Net · SBU testshadow error rate: 3.7 -> 5.3Hurt

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