AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

ReX: An Efficient Approach to Reducing Memory Cost in Image Classification

Xuwei Qian, Renlong Hang, Qingshan Liu

AAAI 2022 · Architectures and efficiency › RNNs and normalization · approach: Dataset condensation and flow estimation · 4 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 early blocks with a ReX layerResNet34 (7 exits) · ImageNet-1kPeak RAM: 3.1MB -> 0.4MB (↓7.75x)Improved
Replace early blocks with a ReX layerMobileNetV2 (6 exits) · ImageNet-1kPeak RAM: 2.3MB -> 245KB (↓11.5x)Improved
Replace early blocks with a ReX layerMobileNetV2 (6 exits) · ImageNet-1kTop-1 accuracy: 71.7 ± 0.24% -> 72.8 ± 0.11%Improved
Use consistency-based early exit instead of confidence-based exitReX-MobileNetV2 (6 exits) · Visual Wake WordsTop-1 accuracy: 89.7% -> 91.0%Improved
Use consistency-based early exit instead of confidence-based exitReX-MobileNetV2 (6 exits) · ImageNet-1kTop-1 accuracy: 71.1% -> 72.8%Improved
Use a 4×4 patch size (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 72.8% -> 71.7%Hurt
Use a 12×12 patch size (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 72.8% -> 72.0%Hurt
Increase stride to 6 (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 72.8% -> 70.5%Hurt
Reduce hidden sizes to h1=8 and h2=8 (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 72.8% -> 71.1%Hurt
Increase hidden sizes to h1=16 and h2=16 (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 72.8% -> 73.1%Improved
Add global vectors V G (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 69.7% -> 72.8%Improved
Add row summary V R (ablation)ReX-MobileNetV2 (6 exits) · ImageNet-1kAccuracy: 70.9% -> 72.8%Improved

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