AI Paper Atlas

Research map / Detection and segmentation / CNN features

Adversarial Fine-Grained Composition Learning for Unseen Attribute-Object Recognition

Kun Wei, Muli Yang, Hao Wang, Cheng Deng, Xianglong Liu

ICCV 2019 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 96 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 quintuplet loss (semi-negative samples) (ablation)base model with triplet loss · MIT-States (unseen pairs)H-Mean accuracy (%): 6.7 -> 12.0Improved
add quintuplet loss (ablation)base model with triplet loss · UT-Zappos (unseen pairs)H-Mean accuracy (%): 15.0 -> 48.8Improved
add adversarial learning (ablation)base model · MIT-States (unseen pairs)H-Mean accuracy (%): 6.7 -> 6.7No clear effect
add adversarial learning (ablation)base model · UT-Zappos (unseen pairs)H-Mean accuracy (%): 15.0 -> 23.3Improved
add multi-scale feature integration (ablation)base model · MIT-States (unseen pairs)H-Mean accuracy (%): 6.7 -> 7.7Improved
add multi-scale feature integration (ablation)base model · UT-Zappos (unseen pairs)H-Mean accuracy (%): 15.0 -> 18.2Improved
add quintuplet loss on top of adversarial learning and Multi (ablation)Ladv + Multi · MIT-States (unseen pairs)H-Mean accuracy (%): 8.4 -> 14.0Improved
add quintuplet loss on top of adversarial learning and Multi (ablation)Ladv + Multi · UT-Zappos (unseen pairs)H-Mean accuracy (%): 24.9 -> 50.7Improved
add adversarial learning on top of quintuplet loss and Multi (ablation)Lquin + Multi · MIT-States (unseen pairs)H-Mean accuracy (%): 13.5 -> 14.0Improved
add adversarial learning on top of quintuplet loss and Multi (ablation)Lquin + Multi · UT-Zappos (unseen pairs)H-Mean accuracy (%): 49.3 -> 50.7Improved
add multi-scale feature integration to full model without it (ablation)Lquin + Ladv · MIT-States (unseen pairs)H-Mean accuracy (%): 13.1 -> 14.0Improved
add multi-scale feature integration to full model without it (ablation)Lquin + Ladv · UT-Zappos (unseen pairs)H-Mean accuracy (%): 50.2 -> 50.7Improved

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