AI Paper Atlas

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

A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications

Yun-Hao Cao, Jianxin Wu

AAAI 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 27 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 Tobias-guided background replacement to MoCov2 pretrainingResNet-50 on CUB-200 · CUB-200, Mixup fine-tuning, 200 pretraining epochsaccuracy (%): 53.0 -> 62.0 (+9.0)Improved
Add Tobias-guided background replacement to SimCLR pretrainingResNet-50 on CUB-200 · CUB-200, Mixup fine-tuning, 200 pretraining epochsaccuracy (%): 66.5 -> 71.7 (+5.2)Improved
Add Tobias-guided background replacement to MoCov2 pretrainingResNet-50 pretrained on ImageNet · Pascal VOC trainval07+12, R-50-FPNAP75: 60.5 -> 61.1Improved
Add Tobias-guided background replacement to MoCov2 pretrainingResNet-50 on IN-100k · VOC 07&12, 200 epochsAP75: 51.6 -> 53.9 (+2.3)Improved
Remove Tobias foreground/background guidance and merge patches randomly (ablation)MoCov2-Tobias on IN-10k · VOC 07&12, 800 epochsAP50: 73.2 -> 72.0 (↓1.2)Hurt
Replace Tobias-guided merging with Mixup (ablation)MoCov2-Tobias on IN-10k · VOC 07&12, 800 epochsAP50: 73.2 -> 70.9 (↓2.3)Hurt
Increase background replacement probability to p=0.5 (ablation)MoCov2-Tobias on IN-10k · VOC 07&12, 800 epochsAP75: 45.9 -> 49.4Improved
Set background replacement probability to p=0.7 (ablation)MoCov2-Tobias on IN-10k · Tiny-IN-200, 800 epochslinear evaluation accuracy (%): 23.6 -> 25.4Improved
Reduce ResNet-50 depth to bottleneck configuration [1,2,3,1] (ablation)Random ResNet-50 localization · ImageNetlocalization accuracy (%): 48.2±0.6 -> 43.9±1.5Hurt
Increase ResNet-50 depth to bottleneck configuration [6,8,12,6] (ablation)Random ResNet-50 localization · CUB-200localization accuracy (%): 41.8±0.6 -> 45.0±0.9Improved
Replace ReLU with sigmoid (ablation)Random ResNet-50 localization · CUB-200localization accuracy (%): 41.8±0.6 -> 22.6±3.3Hurt
Remove skip connections (ablation)Random ResNet-50 localization · ImageNetlocalization accuracy (%): 48.2±0.6 -> 50.8±1.0No clear effect

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