AI Paper Atlas

Research map / Detection and segmentation / CNN features

iNAS: Integral NAS for Device-Aware Salient Object Detection

Yu-Chao Gu, Shang-Hua Gao, Xu-Sheng Cao, Peng Du, Shao-Ping Lu, Ming-Ming Cheng

ICCV 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 15 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
add searchable backbone (ablation)fixed backbone + fixed head · CPU latency, ECSSDlatency (ms): 45.17 -> 41.20Improved
add searchable saliency head (ablation)fixed backbone + fixed head · CPU latency, ECSSDlatency (ms): 45.17 -> 36.20Improved
search backbone and head jointly (integral space) (ablation)fixed backbone + fixed head · CPU latency, ECSSDlatency (ms): 45.17 -> 33.06Improved
search backbone and head jointly (integral space) (ablation)fastest architecture · ECSSDmaxF: 0.941 -> 0.944Improved
search backbone and head jointly (integral space) (ablation)best-performance architecture · ECSSDmaxF: 0.941 -> 0.947Improved
search only the backbone (ablation)fixed backbone + fixed head · ECSSDmaxF: 0.941 -> 0.941No clear effect
use latency-group sampling instead of uniform sampling in evolution search (ablation)evolution search · search space latency rangecoverage of latency range: 50.2% -> 99%Improved
use device-aware search on CPU instead of GPU-searched model (ablation)iNAS(GPU)-L · CPU latencylatency (ms): 48.90 -> 42.99Improved
use device-aware search on mobile phone instead of GPU-searched model (ablation)iNAS(GPU)-L · Mobile latencylatency (ms): 397.17 -> 339.61Improved
use device-aware search on embedded device instead of GPU-searched model (ablation)iNAS(GPU)-L · Embedded latencylatency (ms): 71.70 -> 63.39Improved
use searchable multi-scale unit instead of inverted bottleneck (ablation)search space · latency-maxF Pareto frontier (Fig. 10)maxF vs latencyImproved
increase backbone complexity (ablation)iNAS sampled models · 2000 sampled models (Fig. 11)performanceImproved

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