AI Paper Atlas

Research map / Detection and segmentation / CNN features

Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion

Adam Kortylewski, Qing Liu, Angtian Wang, Yihong Sun, Alan Yuille

IJCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 102 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
replace fully connected head with compositional model (CompNet-RXT-RB4)ResNext · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 83.4 -> 94.1Improved
add generative regularization of vMF kernels (gamma1=3) (ablation)CompNet-ResNext-RB4 without regularization · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 84.4 -> 93.0Improved
add generative regularization of mixture components (gamma2=3) (ablation)CompNet-ResNext-RB4 without regularization · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 84.4 -> 90.1Improved
add mixture-component regularization to vMF regularization (ablation)CompNet-ResNext-RB4 · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 93.0 -> 94.1Improved
add vMF-kernel regularization to mixture regularization (ablation)CompNet-ResNext-RB4 · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 90.1 -> 94.1Improved
end-to-end training with regularization after initialization (ablation)CompNet-ResNext-RB4 · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 87.0 -> 94.1Improved
learn from RB4 instead of RB3 of ResNext (ablation)CompositionalNet · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 88.8 -> 94.1Improved
use pool4 instead of pool5 of VGG (ablation)CompNet-VGG · Occluded-P3D+-Vehicles classification (mean over L0-L3)accuracy: 93.0 -> 92.2No clear effect
add CutPaste occlusion augmentation to trainingResNext · Occluded-COCO-Vehicles classification (avg L0-L3)accuracy: 88.5 -> 94.1Improved
add CutPaste occlusion augmentation to trainingCompNet-RXT-RB4 · Occluded-COCO-Vehicles classification (avg L0-L3)accuracy: 94.8 -> 95.0No clear effect
reduce context weight from omega=0.5 to 0.2 (ablation)CompNet-VGG-p4 · Occluded-P3D+-Vehicles detection (mean AP@IoU0.5)AP@IoU0.5: 76.6 -> 81.3Improved
reduce context weight from omega=0.5 to 0.2 (ablation)CompNet-VGG-p4 · Occluded-COCO-Vehicles detection (avg AP@IoU0.5)AP@IoU0.5: 61.1 -> 72.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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