AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures

Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun

ECCV 2018 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 200 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
select models by accuracy only (PNAS criterion) instead of device-aware Pareto selection (ablation)DPP-Net search · CIFAR-10mobile inference time (s): 0.912 vs 0.149Hurt
device-aware Pareto selection with workstation timing instead of PNAS criterion (ablation)DPP-Net search · CIFAR-10error rate (%): 4.36 -> 4.78Hurt
add memory usage as fifth objective for mobile search (Panacea/M models) (ablation)DPP-Net-M · CIFAR-10memory on mobile (Mem-M): 213MB -> 58MBImproved
DPP-Net-Panacea instead of CondenseNet-86CIFAR-10 classifier · CIFAR-10error rate (%): 5.0 -> 4.62 ± 0.23Improved
DPP-Net-Panacea instead of CondenseNet-86CIFAR-10 classifier · CIFAR-10FLOPs: 65.8M -> 63.5MMixed
transfer DPP-Net-Panacea to ImageNet instead of CondenseNet-74ImageNet classifier · ImageNettop-1 error (%): 26.2 -> 25.98Improved
DPP-Net-Panacea instead of NASNet (Mobile)ImageNet classifier · ImageNettop-1 error (%): 26.0 -> 25.98Improved
use DPP-Net-Panacea instead of CondenseNet-74 on mobile phoneImageNet classifier · ImageNetmobile inference time (s): 0.694 -> 0.676Improved
search on the target device itself rather than reusing another device's resultsDPP-Net search · 4-layer cell modelsinference time rank across devicesImproved
fewer parameters or FLOPsDPP-Net models · CIFAR-10inference timeNo clear effect
DPP-Net-ES (2.04M params) vs DPP-Net-WS (1.00M params) on embedded device (ablation)DPP-Net · CIFAR-10embedded-system time (s): 0.075 -> 0.044Improved

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