AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object Proposal Generation Using Two-Stage Cascade SVMs

Ziming Zhang, Philip H. S. Torr

TPAMI 2016 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 24 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 l1-norm SVMs without ranking constraints (l1-o/r) in both stages (ablation)two-stage cascade · VOC2007 recall-proposalobject recallImproved
use l1-o/r in Stage I instead of ranking SVMs (ablation)Stage I classifier · VOC2007 recall-overlapAUCImproved
use l2-w/r or l1-o/r in Stage II (ablation)Stage II classifier · VOC2007 recall-overlapAUCImproved
increase number of quantized scales K from 36 to 121 to 196 (eta 0.5, 0.67, 0.75) (ablation)quantization scheme · VOC2007AUC at 1000 proposalsImproved
increase K (ablation)quantization scheme · VOC2007AUC at 1, 10, 100 proposalsNo clear effect
increase K (ablation)quantization scheme · VOC2007computational timeHurt
use previously proposed ranking cascade setting instead of best l1-o/r setting (ablation)cascade SVMs · VOC2007recall-overlap AUCHurt
use gradient features with linear filters instead of Baseline Aobject proposal pipeline · VOC2007computational time (s): 3.58 -> 0.20Improved
use cascade SVMs instead of Baseline Aobject proposal pipeline · VOC2007 (1000 proposals)object recall (%): 88.6 -> 93.8Improved
use cascade SVMs instead of Baseline Bobject proposal pipeline · VOC2007 (1000 proposals)object recall (%): 77.7 -> 93.8Improved
use cascade SVMs instead of Baseline B (structured learning)object proposal pipeline · VOC2007 (1000 proposals)AUC objects: 67.4 -> 64.5Hurt
use cascade SVMs instead of objectness on unseen categoriesobject proposal pipeline · VOC2007 (14 unseen categories, 10 proposals)object recall (%): 41.0 -> 46.4Improved

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