AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning With Side Information Through Modality Hallucination

Judy Hoffman, Saurabh Gupta, Trevor Darrell

CVPR 2016 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 224 citations (OpenAlex)

Check 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 a depth-supervised hallucination branch to the RGB detectorAlexNet Fast R-CNN · NYUD2 testmAP: 26.6 -> 30.5Improved
Add a depth-supervised VGG-1024 hallucination branchAlexNet RGB detector with VGG-1024 hallucination network · NYUD2 testmAP: 29.9 -> 34.0Improved
Use a depth-initialized rather than randomly initialized hallucination network (ablation)AlexNet hallucination detector · NYUD2 valmAP: 20.3 -> 24.2Improved
Use depth-network rather than RGB-network initialization (ablation)AlexNet hallucination detector · NYUD2 valmAP: 22.4 -> 24.2Improved
Place the hallucination loss at pool5 instead of pool1 (ablation)AlexNet hallucination detector · NYUD2 valmAP: 22.3 -> 24.2Improved
Place the hallucination loss at pool5 instead of pool2 (ablation)AlexNet hallucination detector · NYUD2 valmAP: 21.5 -> 24.2Improved
Place the hallucination loss at pool5 instead of fc6 (ablation)AlexNet hallucination detector · NYUD2 valmAP: 20.4 -> 24.2Improved
Add the NYUD2-trained hallucination branchRGB detector applied to PASCAL VOC 2007 · PASCAL VOC 2007 testmAP: 16.9 -> 20.8Improved
Add the NYUD2-trained hallucination branch after RGB fine-tuning on PASCALPASCAL-fine-tuned RGB detector · PASCAL VOC 2007 testmAP: 52.1 -> 53.4Improved
Use depth-estimated pixels as input to the depth channel instead of feature hallucinationPre-trained RGB-D detector · NYUD2mAP: 22% mAP vs 27% mAPHurt
Combine two RGB models rather than using a single RGB modelRGB detector · NYUD2 testmAP: 26.6 -> 29.0Improved

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