AI Paper Atlas

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

Towards Partial Supervision for Generic Object Counting in Natural Scenes

Hisham Cholakkal, Guolei Sun, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Luc Van Gool

TPAMI 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 14 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 dual-branch (classification + density) architecture instead of CAM+MSE regression (ablation)LC framework · PASCAL VOC 2007 count-testmRMSE: 0.45 -> 0.29Improved
add spatial loss to class + MSE loss (ablation)LC framework · PASCAL VOC 2007 count-testmRMSE-nz: 1.52 -> 1.32Improved
add ranking loss on top of class + spatial + MSE (ablation)LC framework · PASCAL VOC 2007 count-testmRMSE-nz: 1.32 -> 1.14Improved
set ranking loss weight lambda to 0.1 instead of 1 (ablation)LC framework · PASCAL VOC 2007 count-testmRMSE: 0.36 -> 0.29Improved
define lower-count range up to 4 (t=5) instead of up to 2 (t=3) (ablation)LC framework · COCO count-testmRMSEImproved
use ground-truth point annotations for the spatial mask (ablation)LC framework · PASCAL VOC 2007 count-testmRMSE: 0.29 -> 0.28No clear effect
increase number of count-annotated categories from 20 to 80 (ablation)RLC framework · COCO count-testmRMSE: 0.41 -> 0.35Improved
use bottleneck hidden size P/2 instead of P in weight modulation layer (ablation)RLC framework · COCO count-testmRMSE-nz: 1.98 -> 1.94Improved
use 2 layers instead of 3 in weight modulation layer (ablation)RLC framework · COCO count-testmRMSE-nz: 2.07 -> 1.98Improved
use softmax instead of ReLU activation in weight modulation layer (ablation)RLC framework · COCO count-testmRMSE-nz: 1.97 -> 1.94Improved
block backpropagation from weight modulation layer to classifier (ablation)RLC framework · COCO count-test (60/20 split)mRMSE: 0.38 -> 0.36Improved
multiply category-specific density by total density map D_tot (ablation)RLC framework · COCO count-test (60/20 split)mRMSE: 0.37 -> 0.36Improved

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