AI Paper Atlas

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

Online Refinement of Low-Level Feature Based Activation Map for Weakly Supervised Object Localization

Jinheng Xie, Cheng Luo, Xiangping Zhu, Ziqi Jin, Weizeng Lu, Linlin Shen

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 73 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 the evaluator supervised by evaluation loss in stage two (ablation)stage-one activation map generator · CUB-200-2011CorLoc: 64.52 -> 71.35Improved
add weighted entropy loss to evaluation loss (ablation)ORNet stage two · CUB-200-2011CorLoc: 71.35 -> 81.68Improved
add weighted entropy loss to evaluation loss (ablation)ORNet stage two · CUB-200-2011Top-1 LocErr: 44.36 -> 36.05Improved
add area loss to evaluation loss alone (ablation)ORNet stage two · CUB-200-2011CorLoc: 71.35 -> 72.11No clear effect
add attentive erasing to evaluation loss alone (ablation)ORNet stage two · CUB-200-2011CorLoc: 71.35 -> 69.14Hurt
add area loss and attentive erasing together (ablation)Le · CUB-200-2011CorLoc: 71.35 -> 76.68Improved
add weighted entropy loss on top of area loss and attentive erasing (ablation)Le+La+AE · CUB-200-2011CorLoc: 76.68 -> 86.19Improved
add area loss on top of weighted entropy loss and attentive erasing (ablation)Le+Lw+AE · CUB-200-2011CorLoc: 85.09 -> 86.19Improved
add attentive erasing on top of weighted entropy loss and area loss (ablation)Le+Lw+La · CUB-200-2011CorLoc: 80.10 -> 86.19Improved
use weighted entropy loss instead of plain mean entropy loss (ablation)Le+La+AE · CUB-200-2011CorLoc: 72.89 -> 86.19Improved
use weighted entropy loss instead of plain mean entropy loss (ablation)Le+La+AE · CUB-200-2011Top-1 LocErr: 42.53 -> 32.26Improved
vary threshold from 0.2 to 0.8 (ablation)ORNet · CUB-200-2011 and ImageNet-1KCorLocNo clear effect

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