AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Seeing Into Darkness: Scotopic Visual Recognition

Bo Chen, Pietro Perona

CVPR 2017 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs · 6 citations (OpenAlex)

Check 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 time-adapted first-layer features instead of time-normalized rates (ablation)WaldNet versus Rate classifier · MNIST and CIFAR10speed-accuracy tradeoffImproved
Train with scotopic images and use an appropriate stopping criterion instead of retrofitting a photopic classifier (ablation)WaldNet versus Photopic classifier · MNIST and CIFAR10speed-accuracy tradeoffImproved
Replace a fixed interrogation duration with free-response stopping (ablation)Scotopic classifiers · MNIST and CIFAR10median photon counts: 3× reductionImproved
Learn dynamic stopping thresholds instead of using constant thresholds (ablation)Scotopic classifiers · MNIST and CIFAR10average PPP at a given error rateImproved
Use learned dynamic thresholds instead of constant thresholds (ablation)Scotopic classifiers · CIFAR10median PPPHurt
Use a single time-adapted network instead of an ensemble of specialists (ablation)WaldNet versus Ensemble · MNIST, free-responsespeed-accuracy tradeoffNo clear effect
Use a single time-adapted network instead of an ensemble of specialists (ablation)WaldNet versus Ensemble · CIFAR10, lowlight conditions (≤ 22 PPP)speed-accuracy tradeoffImproved
Increase dark current to 11% (ablation)WaldNet · MNIST and CIFAR10exposure time: doublesHurt
Increase read noise to 22% (ablation)WaldNet · MNISTaccuracyNo clear effect
Increase read noise to 22% (ablation)WaldNet · CIFAR10accuracyHurt
Increase read noise to 50% (ablation)WaldNet · MNIST and CIFAR10accuracyHurt
Increase rotational jitter to 22° at 220 PPP (ablation)WaldNet · MNIST and CIFAR10accuracyHurt

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