AI Paper Atlas

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

Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization

Stefan Stojanov, Ngoc Anh Thai, Zixuan Huang, James Matthew Rehg

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 1 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
Train on ABC using local patch correspondences rather than global instance-level featuresDOPE versus VISPE++ - MoCoV2 · ModelNet40-LS, 5-way 1-shotaccuracy: 61.07 \ci{0.41} -> 62.76 \ci{0.43}Improved
Train on ABC using local patch correspondences rather than global instance-level featuresDOPE versus VISPE++ - SimSiam · ModelNet40-LS, 5-way 5-shotaccuracy: 76.55 \ci{0.22} -> 76.86 \ci{0.33}Improved
Train on ABC using local patch correspondences rather than global instance-level featuresDOPE versus VISPE++ - MoCoV2 · ShapeNet-LS, 5-way 1-shotaccuracy: 58.99 \ci{0.46} -> 62.00 \ci{0.48}Improved
Train on ABC using local patch correspondences rather than global instance-level featuresDOPE versus VISPE++ - MoCoV2 · ShapeNet-LS, 5-way 5-shotaccuracy: 72.26 \ci{0.39} -> 73.55 \ci{0.38}Improved
Use local patch matching rather than supervised FEATDOPE versus FEAT · CO3D-LS, 5-way 1-shotaccuracy: 64.48 \ci{0.43} -> 61.77 \ci{0.44}Hurt
Use local patch matching rather than supervised RFSDOPE versus RFS · CO3D-LS, 5-way 5-shotaccuracy: 81.50 \ci{0.26} -> 75.16 \ci{0.32}Hurt
Include negatives from other object instances as well as the second view (ablation)DOPE · ModelNet40-LS, 5-way 1-shotaccuracy: 61.51 \ci{0.42} -> 62.76 \ci{0.43}Improved
Include negatives from the second view as well as other objects (ablation)DOPE · ModelNet40-LS, 5-way 1-shotaccuracy: 43.50 \ci{0.39} -> 62.76 \ci{0.43}Improved
Train with physically distinct object viewpoints rather than two augmentations of one image (ablation)DOPE · ModelNet40-LS, 5-way 1-shotaccuracy: 38.36 \ci{0.43} -> 62.76 \ci{0.43}Improved
Add random background removal during training (ablation)DOPE · ModelNet validation classes, 1-shot 5-wayaccuracy: 54.24 -> 61.78Improved
Add mask prediction and mask local feature encodings (ablation)DOPE · ModelNet validation classes, 1-shot 5-wayaccuracy: 50.06 -> 61.78Improved
Replace known foreground masks with FreeSOLO-predicted masks (ablation)DOPE - ABC · ModelNet40-LS, 5-way 1-shotaccuracy: 62.76 \ci{0.43} -> 57.63 \ci{0.40}Hurt

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