AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-Powered Intelligent PhlatCam

Yonggan Fu, Yang Zhang, Yue Wang, Zhihan Lu, Vivek Boominathan, Ashok Veeraraghavan, Yingyan Lin

ICCV 2021 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 5 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
co-optimize the phase mask with the CNN via NAS instead of fixed Gabor maskSACoD (6 masks) · CIFAR-100accuracy (%): +5.46% higher accuracy, 64.1% fewer FLOPsImproved
co-search the backend architecture with the mask instead of fixed MobileNetV2 Co-trainSACoD (6 masks) · CIFAR-10accuracy (%): +0.01% accuracy, 44.1% fewer FLOPsImproved
co-search the backend architecture with the mask instead of fixed Gabor maskSACoD (6 masks) · CIFAR-10accuracy (%): +1.45% accuracy, 70.9% fewer FLOPsImproved
use SACoD instead of Gabor-mask under extremely low FLOPs/energySACoD · FlatCam Faceaccuracy (%): +8.75% higher accuracyImproved
use SACoD instead of Gabor-mask under extremely low FLOPs/energySACoD · Head Poseaccuracy (%): +5.85% higher accuracyImproved
use SACoD instead of Co-train on segmentation with 6 masksSACoD · CityscapesmIOU: 68.8 -> 71.6Improved
use SACoD instead of Co-train on horse2zebra with 2 masksSACoD · horse2zebraFID: 66.82 -> 89.80Hurt
use SACoD instead of Gabor-mask on horse2zebra with 4 masksSACoD · horse2zebraFID: 106.27 -> 86.00Improved
use fabricated masks instead of simulated masksSACoD · CIFAR-10accuracy (%): 94.41 -> 90.02Hurt
use SACoD masks instead of Gabor-mask in fabricated systemSACoD · CIFAR-10 (fabricated)accuracy (%): 87.17 -> 90.02Improved
customize the mask per task instead of transferring masks from FlatCam Face (ablation)SACoD · CIFAR-10accuracy (%): 93.10 -> 94.41Improved
customize the mask per task instead of transferring masks from FlatCam Face (ablation)SACoD · CIFAR-100accuracy (%): 72.50 -> 76.67Improved

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