AI Paper Atlas

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

Deliberative Explanations: visualizing network insecurities

Pei Wang, Nuno Nvasconcelos

NeurIPS 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 7 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 hesitancy score with hardness score (ablation)difficulty score · ADE20KADE20K IoU precision (avg): 21.79(0.03) -> 23.80(0.19)Improved
Replace entropy score with hardness score (ablation)difficulty score · ADE20KADE20K IoU precision (avg): 20.73(0.09) -> 23.80(0.19)Improved
Use second-order gradient-Hessian instead of first-order gradient (ablation)attribution function · ADE20KADE20K IoU precision (avg): 23.80(0.19) -> 24.26(0.30)No clear effect
Use second-order gradient-Hessian instead of first-order gradient (ablation)attribution function · CUB200CUB200 precision-recallImproved
Use integrated gradient instead of first-order gradient (ablation)attribution function · ADE20KADE20K IoU precision (avg): 23.80(0.19) -> 23.99(0.24)No clear effect
Add difficulty-score attribution map to gradient (vs gradient w/o ms) (ablation)gradient attribution · ADE20KADE20K IoU precision (avg): 23.33(0.82) -> 23.80(0.19)Improved
Use ResNet50 instead of VGG16 backbone (ablation)deliberative explanations · ADE20KADE20K IoU precision (avg): 23.80(0.19) -> 22.60(0.22)Hurt
Use ResNet50 instead of AlexNet backbone (ablation)deliberative explanations · CUB200CUB200 precision-recallImproved
Use ResNet50 instead of VGG16 backbone (ablation)deliberative explanations · CUB200CUB200 precision-recallImproved
Use VGG16 instead of AlexNet backbone (ablation)deliberative explanations · ADE20KADE20K IoU precision (avg): 22.55(0.65) -> 23.80(0.19)Improved
Show algorithm insecurities instead of random crops to turkers (ablation)MTurk evaluation · MTurkagreement with algorithm: 26.3% -> 51.9%Improved
Show algorithm insecurities instead of random crops to turkers (ablation)MTurk evaluation · MTurkturker mutual agreement: 33.7% -> 59.4%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