AI Paper Atlas

Research map / Detection and segmentation / CNN features

Efficient Scale-Permuted Backbone with Learned Resource Distribution

Xianzhi Du, Tsung-Yi Lin, Pengchong Jin, Yin Cui Mingxing Tan, Quoc Le, Xiaodan Song

ECCV 2020 · Detection and segmentation › CNN features · approach: Efficient network training and design · 3 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
learn resource distribution over blocks (ablation)SP-EfficientNet-B0 · COCO val2017 RetinaNetAP: 33.0 -> 33.8Improved
learn resource distribution (parameters) (ablation)SP-EfficientNet-B0 · COCO val2017parameters: 4.4M -> 3.6MImproved
add space-to-depth resampling (ablation)Eff-SpineNet-D0 · COCO val2017 RetinaNetAP: 33.1 -> 33.8Improved
add weighted block fusion (ablation)Eff-SpineNet-D0 · COCO val2017 RetinaNetAP: 32.8 -> 33.1Improved
add stochastic depth (ablation)Eff-SpineNet-D2 · COCO val2017AP: +0.4Improved
replace ReLU with Swish (ablation)Eff-SpineNet-D2 · COCO val2017AP: +2.0Improved
use large-scale multi-scale training with extended schedule (ablation)Eff-SpineNet-D2 · COCO val2017AP: 32.6 -> 40.1 (+7.4)Improved
add squeeze and excitation (ablation)Eff-SpineNet-D2 · COCO val2017AP: 32.2 -> 32.6 (+0.4)Improved
apply the same training strategies to ResNet-50-FPN: multi-scale training (ablation)ResNet-50-FPN · COCO val2017AP: 37.0 -> 40.4 (+3.4)Improved
apply stochastic depth to ResNet-50-FPN (ablation)ResNet-50-FPN · COCO val2017AP: 40.7 -> 42.3 (+1.6)Improved
lengthen training from 72 to 650 epochs (ablation)Eff-SpineNet-D2 · COCO val2017AP: 34.8 -> 42.5Improved
use scale-permuted topology instead of EfficientNet-FPNEff-SpineNet-D0 · COCO val2017 RetinaNetAP: 33.5 -> 34.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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