AI Paper Atlas

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

Geometry Constrained Weakly Supervised Object Localization

Weizeng Lu, Xi Jia, Weicheng Xie, Linlin Shen, Yicong Zhou, Jinming Duan

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 90 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 background (negative-entropy) loss Lb to Lo (ablation)GC-Net · CUB-200-2011 (VGG16, learning-driven rotated ellipse)Top-1 LocErr (%): 59.22 -> 47.03Improved
add area loss La to Lo+Lb (ablation)GC-Net · CUB-200-2011 (VGG16, learning-driven rotated ellipse)Top-1 LocErr (%): 47.03 -> 41.15Improved
add area loss La alone to Lo (ablation)GC-Net · CUB-200-2011 (VGG16, learning-driven rotated ellipse)Top-1 LocErr (%): 59.22 -> 69.89Hurt
add Lb to Lo+La (ablation)GC-Net · CUB-200-2011 (VGG16, learning-driven rotated ellipse)CorLoc (%): 39.89 -> 74.89Improved
use rotated rectangle instead of rectangle (learning-driven) (ablation)GC-Net · CUB-200-2011 (VGG16)Top-1 LocErr (%): 44.35 -> 36.76Improved
use rotated ellipse instead of rectangle (learning-driven) (ablation)GC-Net · CUB-200-2011 (VGG16)Top-1 LocErr (%): 44.35 -> 41.15Improved
use rotated rectangle instead of rectangle (model-driven) (ablation)GC-Net · CUB-200-2011 (VGG16)Top-1 LocErr (%): 44.10 -> 44.25No clear effect
use learning-driven instead of model-driven generator (rotated rectangle) (ablation)GC-Net · CUB-200-2011 (VGG16)Top-1 LocErr (%): 44.25 -> 36.76Improved
use learning-driven instead of model-driven generator (rotated ellipse) (ablation)GC-Net · CUB-200-2011 (VGG16)Top-1 LocErr (%): 41.73 -> 41.15Improved
use GC-Net-Rect-VGG instead of DA-Net-VGGGC-Net · CUB-200-2011CorLoc (%): 67.7 -> 81.1Improved
use GC-Net-Rect with Inception-V3 instead of DA-Net on ILSVRC2012GC-Net · ILSVRC2012 valTop-1 LocErr (%): 52.47 -> 50.94No 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