AI Paper Atlas

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

An Adversarial Approach to Hard Triplet Generation

Yiru Zhao, Zhongming Jin, Guo-jun Qi, Hongtao Lu, Xian-sheng Hua

ECCV 2018 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images · 110 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
replace OHEM mining with adversarial hard triplet generation (HTG)ResNet-18 triplet+softmax · CARS196Recall@1 (%): 68.2 -> 70.6Improved
add OHEM hard mining over random samplingResNet-18 triplet+softmax · CARS196Recall@1 (%): 66.6 -> 68.2Improved
add HTG over random samplingResNet-18 triplet+softmax · CARS196Recall@1 (%): 66.6 -> 70.6Improved
remove the bias from the softmax layer (ablation)ResNet-18 with HTG · CARS196Recall@1 (%): 69.3 -> 70.6Improved
remove the bias from the softmax layer (ablation)ResNet-18 with random sampling · CARS196Recall@1 (%): 65.4 -> 66.6Improved
remove the bias from the softmax layer (ablation)ResNet-18 with OHEM · CARS196Recall@1 (%): 67.1 -> 68.2Improved
add keypoint maps (KPM) local branch to HTG (ablation)ResNet-18 with HTG · CARS196Recall@1 (%): 70.6 -> 76.5Improved
add K-Branch local branch to HTG (ablation)ResNet-18 with HTG · CARS196Recall@1 (%): 70.6 -> 72.7Improved
add ResAttention to HTG (ablation)ResNet-18 with HTG · CARS196Recall@1 (%): 70.6 -> 73.9Improved
add OHEM mining on attention models (vs random)KPM model · CARS196Recall@1 (%): 72.7 -> 72.5No clear effect
add OHEM mining on attention models (vs random)K-Branch model · CARS196Recall@1 (%): 71.9 -> 72.2No clear effect
HTG versus HDCHTG · CUB200Recall@1 (%): 53.6 -> 59.5Improved

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