AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Processing Megapixel Images with Deep Attention-Sampling Models

Angelos Katharopoulos, Francois Fleuret

ICML 2019 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 21 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
Use attention sampling instead of processing all grid patches with Deep MILColon cancer classification · Colon cancertest error: 0.093 ± 0.004 -> 0.093 ± 0.014No clear effect
Use attention sampling instead of processing all grid patches with Deep MILColon cancer classification · Colon cancertime/sample: 48.5 ms -> 1.8 msImproved
Use attention sampling instead of processing all grid patches with Deep MILColon cancer classification · Colon cancermemory/sample: 644 MB -> 21 MBImproved
Use attention sampling instead of processing all grid patches with Deep MILSpeed limit sign classification · Speed limitstest error: 0.083 ± 0.006 -> 0.089 ± 0.002No clear effect
Use attention sampling instead of processing all grid patches with Deep MILSpeed limit sign classification · Speed limitstime/sample: 97.2 ms -> 8.5 msImproved
Use attention sampling instead of processing all grid patches with Deep MILSpeed limit sign classification · Speed limitsmemory/sample: 1,497 MB -> 86 MBImproved
Reduce sampled patches from 10 to 5 (ablation)ATS · Speed limitstest error: 0.095 ± 0.008 -> 0.089 ± 0.002Improved
Remove the entropy regularizer (ablation)ATS · Colon cancerattention explorationHurt
Increase the entropy regularizer weight (ablation)ATS · Colon cancerattention explorationMixed
Vary the number of sampled patches during training (ablation)ATS · Colon cancerlearned attention distributionNo clear effect

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