AI Paper Atlas

Research map / Detection and segmentation / CNN features

Chained Cascade Network for Object Detection

Wanli Ouyang, Kun Wang, Xin Zhu, Xiaogang Wang

ICCV 2017 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 84 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 2 extra cascade stages with classifier chaining (ablation)BN-Net+FRCN · ImageNet val2mAP: 49.4 -> 50.5Improved
add 4 extra cascade stages with classifier chaining (ablation)BN-Net+FRCN · ImageNet val2mAP: 49.4 -> 50.9Improved
add classifier chaining (use previous stage scores) to 4 extra cascade stages (ablation)BN-Net cascade · ImageNet val2mAP: 50.5 -> 50.9Improved
add cascade chaining on top of multi-region features (ablation)BN-Net · ImageNet val2mAP: 50.5 -> 51.3Improved
add cascade chaining on top of multi-region features (ablation)BN-Net · VOC07 testmAP: 73.8 -> 75.2Improved
add feature chaining on top of cascade and classifier chaining (ablation)BN-Net · ImageNet val2mAP: 51.3 -> 54.5Improved
add feature chaining on top of cascade and classifier chaining (ablation)BN-Net · VOC07 testmAP: 75.2 -> 77.1Improved
add multi-region features without chaining or cascade (ablation)BN-Net · VOC07 testmAP: 70.8 -> 73.8Improved
add multi-region features without chaining or cascade (ablation)BN-Net · ImageNet val2mAP: 49.4 -> 50.5Improved
learn scaling vectors a and b instead of fixing them to 1 (ablation)CC-Net · ImageNet val2mAP: drop by 1.7%Improved
replace scaling vector a with fully connected layer with C1C2 parameters (ablation)CC-Net feature chaining · ImageNet val2mAPNo clear effect
CC-Net feature chaining vs GBD-Net message passing when all features share the same contextual regionBN-Net · ImageNet val2mAP: 50.2% -> 52%Improved

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