AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Information Entropy Based Feature Pooling for Convolutional Neural Networks

Weitao Wan, Jiansheng Chen, Tianpeng Li, Yiqing Huang, Jingqi Tian, Cheng Yu, Youze Xue

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 40 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
use EP at inference only on pre-trained ResNet-50 (ablation)ResNet-50 · ImageNet val (10-crop)top-1 error (%): 22.85 -> 22.73Improved
train with EP instead of inference-only EP (ResNet-50) (ablation)ResNet-50 with EP inference · ImageNet val (10-crop)top-1 error (%): 22.73 -> 22.64Improved
add multi-level BEW layers to EP (ResNet-50) (ablation)ResNet-50 + EP · ImageNet val (10-crop)top-1 error (%): 22.64 -> 22.45Improved
add multi-level BEW to VGG-16VGG-16 · ImageNet val (10-crop)top-1 error (%): 28.07 -> 24.78Improved
replace GAP with EP and add BEW in VGG-GAPVGG-GAP · ImageNet val (10-crop)top-1 error (%): 31.66 -> 30.04Improved
add multi-level BEW + EP to InceptionV3InceptionV3 · ImageNet val (10-crop)top-1 error (%): 20.20 -> 19.92Improved
add EP to iSQRT-COV pooling (ResNet-50)iSQRT-COV · ImageNet val (one-crop)top-1 error (%): 22.14 -> 21.97Improved
add BEW + EP to SENet (ResNet-152)SENet · ImageNet val (one-crop)top-1 error (%): 21.57 -> 21.08Improved
add BEW to VGG-16 for scene recognitionVGG-16 · Places365 val (10-crop)top-1 error (%): 44.76 -> 43.36Improved
use ResNet-50 + BEW + EP versus deeper ResNet-152ResNet-152 · Places365 val (10-crop)top-1 error (%): 45.26 -> 43.75Improved
use entropy weights instead of CAM for localization (ResNet-50)ResNet-50 + CAM · ImageNet val localizationtop-1 localization error (%): 51.12 -> 50.15Improved
add EP to DSRG seed generationDSRG · VOC 2012 valmIoU (%): 59.0 -> 61.5Improved

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