AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Query-Driven Multi-Instance Learning

Yen-Chi Hsu, Cheng-Yao Hong, Ming-Sui Lee, Tyng-Luh Liu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 2 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 attention regularization L2 (1 query) (ablation)qMIL · CIFAR10, 1 queryaccuracy: 82.4 ± 1.7 -> 89.9 ± 1.7No clear effect
add attention regularization L2 (3 queries) (ablation)qMIL · CIFAR10, 3 queriesaccuracy: 81.22 ± 1.8 -> 81.77 ± 1.4No clear effect
add attention regularization L2 (5 queries) (ablation)qMIL · CIFAR10, 5 queriesaccuracy: 71.23 ± 3.4 -> 79.45 ± 2.7Improved
add attention regularization L2 (7 queries) (ablation)qMIL · CIFAR10, 7 queriesaccuracy: 65.66 ± 4.6 -> 82.09 ± 2.1Improved
add attention regularization L2 (10 queries) (ablation)qMIL · CIFAR10, 10 queriesaccuracy: 78.33 ± 2.3 -> 86.14 ± 1.3Improved
add attention regularization L2 (10 queries) (ablation)qMIL · CIFAR10, 10 queriesattention accuracy: 70.64 ± 5.4 -> 89.18 ± 1.0Improved
add attention regularization L2 (7 queries) (ablation)qMIL · CIFAR10, 7 queriesattention accuracy: 45.66 ± 20.3 -> 86.01 ± 1.2Improved
add attention regularization L2 (3 queries) (ablation)qMIL · CIFAR10, 3 queriesattention accuracy: 65.52 ± 9.9 -> 87.22 ± 1.1Improved
replace GatedAttnDMIL with qMIL (5000 training bags)qMIL · CIFAR10 single queryaccuracy: 82.4 ± 1.7 -> 89.9 ± 1.7Improved
replace GatedAttnDMIL with qMIL (100 training bags)qMIL · CIFAR10 single queryaccuracy: 55.1 ± 8.6 -> 56.3 ± 4.5No clear effect
increase training bags from 100 to 5000qMIL · CIFAR10 single queryaccuracy: 56.3 ± 4.5 -> 89.9 ± 1.7Improved
replace deep MIML with qMILqMIL · MIML Sceneaccuracy: 89.45 ± 1.22 -> 90.20 ± 0.96Improved

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