AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer

Haipeng Xiong, Hao Lu, Chengxin Liu, Liang Liu, Zhiguo Cao, Chunhua Shen

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 205 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 division decider (learned division mask) instead of softmax attention fusion (ablation)S-DCNet · ShanghaiTech Part_AMAE: 64.1 -> 58.3Improved
add division decider instead of softmax attention fusion (ablation)S-DCNet · ShanghaiTech Part_AMSE: 109.9 -> 95.0Improved
add spatial divide-and-conquer (S-DC) to classification (ablation)VGG16 count classifier · ShanghaiTech Part_AMAEImproved
add S-DC to regression baseline (ablation)VGG16 count regressor · ShanghaiTech Part_AMAEImproved
constrain regressor output to closed set [0,Cmax] with S-DC rather than open-set output (ablation)regression + S-DC · ShanghaiTech Part_AMAEImproved
reformulate counting as classification (with S-DC) rather than regression (ablation)S-DCNet · ShanghaiTech Part_AMAEImproved
classification without S-DC vs regression (ablation)VGG16 count classifier · ShanghaiTech Part_AMAEHurt
add merging loss L_R^2 on final division output (ablation)S-DCNet · ShanghaiTech Part_AMAEImproved
lower Cmax to smaller quantiles (100% down to 80%) with S-DC (ablation)S-DCNet · ShanghaiTech Part_AMAENo clear effect
lower Cmax quantile without S-DC (ablation)classification baseline · ShanghaiTech Part_AMAEHurt
use Two-Linear partition (finer step 0.05 in (0,0.5]) instead of One-Linear (ablation)S-DCNet · ShanghaiTech Part_AMAEImproved
use two-stage S-DC instead of one stage (ablation)S-DCNet · ShanghaiTech Part_AMAEImproved

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