AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

QAPNet: A Quantum-Attentive Patchwise Network for Robust Medical Image Classification Under Noisy Inputs

Maqsudur Rahman, Jun Zhuang

AAAI 2026 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 1 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 element-wise instance reweighting instead of cross-instance dot-product aggregation (ablation)QAPNet · OASIS (30% noise)accuracy (%): 66.00 -> 79.87Improved
add element-wise instance reweighting instead of cross-instance dot-product aggregation (ablation)QAPNet · PathMNIST (30% noise)accuracy (%): 50.55 -> 71.26Improved
add element-wise instance reweighting instead of cross-instance dot-product aggregation (ablation)QAPNet · OrganAMNIST (30% noise)accuracy (%): 38.88 -> 61.55Improved
add element-wise instance reweighting instead of cross-instance dot-product aggregation (ablation)QAPNet · BloodMNIST (5% noise)accuracy (%): 53.74 -> 52.90Mixed
add element-wise instance reweighting instead of cross-instance dot-product aggregation (ablation)QAPNet · OASIS (5% noise)accuracy (%): 84.60 -> 84.86No clear effect
increase quantum circuit from 4 to 8 qubits (ablation)QAPNet · full dataset, sliding windowaccuracy (%): 78.89 -> 84.89Improved
increase quantum circuit from 4 to 8 qubits (ablation)QAPNet · 1952-sample subset, sliding windowaccuracy (%): 48.62 -> 68.62Improved
use sliding window patch extraction instead of dynamic (15) selection (ablation)QAPNet · full dataset, 8 qubitsaccuracy (%): 79.23 -> 84.89Improved
use sliding window patch extraction instead of dynamic (5) selection (ablation)QAPNet · full dataset, 8 qubitsaccuracy (%): 67.12 -> 84.89Improved
use sliding window instead of random sampling (ablation)QAPNet · full dataset, 8 qubitsaccuracy (%): 81.08 -> 85.00Improved
QAPNet versus SC-MIL under heavy noiseSC-MIL · PathMNIST (30% noise)accuracy (%): 53.59 -> 71.26Improved
QAPNet versus SC-MIL under heavy noiseSC-MIL · OASIS (30% noise)accuracy (%): 59.10 -> 79.87Improved

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