AI Paper Atlas

Research map / Architectures and efficiency / CNN design

A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays

Laurie Bose, Jianing Chen, Stephen J. Carey, Piotr Dudek, Walterio Mayol-Cuevas

ICCV 2019 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 42 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 non-zero ternary threshold (ternary weights) instead of threshold 0 (binary weights) (ablation)Ternary CNN on SCAMP5 · MNIST (SCAMP5)accuracy and convolution time: best accuracy 94.2% at threshold 0.2Improved
raise ternary threshold from 0 to 0.99 (sparser weights) (ablation)Ternary CNN on SCAMP5 · MNIST (SCAMP5)frame rate (fps): 135 -> 210 fpsImproved
raise ternary threshold to 0.99 (only a couple of non-zero weights per kernel) (ablation)Ternary CNN on SCAMP5 · MNIST (SCAMP5)accuracy (%): 94.2% -> 70%Hurt
deploy on SCAMP5 sensor instead of PC evaluationMNIST CNN · MNISTaccuracy (%): 95.4% -> 94.2%Hurt
use non-zero ternary threshold instead of binary weights (ablation)Ternary CNN on SCAMP5 · Car trackinglocalization errorImproved
raise ternary threshold from 0 to 0.99 (ablation)Ternary CNN on SCAMP5 · Car trackingframe rate (fps): 140 -> 250 fpsImproved
raise ternary threshold above 0.5 (ablation)Ternary CNN on SCAMP5 · Car trackinglocalization error: roughly constant for thresholds 0.2 to 0.5, then exponential increaseHurt

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