AI Paper Atlas

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

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects

Chuanruo Ning, Ruihai Wu, Haoran Lu, Kaichun Mo, Hao Dong

NeurIPS 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 6 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
use similarity-guided interactions on novel categoriesWhere2Explore · Novel categories, pushing and pullingF-score: 35.4 / 38.5 / 41.6; 12.1 / 12.5 / 24.2Improved
use similarity-guided interactions on novel categoriesWhere2Explore · Novel categories, pushing and pullingSample successful rate: 31.3 / 37.3 / 39.5; 11.5 / 13.4 / 14.9Improved
add similarity-guided few-shot exploration (ablation)No-explore affordance model · Novel categoriesF-score: 20.6; 3.9Improved
replace similarity-guided exploration with random interactions (ablation)Where2Explore · Novel categories, pushing and pullingF-score: 24.9 / 28.8 / 29.0; 4.0 / 6.1 / 9.2Hurt
replace similarity-guided exploration with random interactions (ablation)Where2Explore · Novel categories, pushing and pullingSample successful rate: 15.0 / 18.4 / 21.6; 3.4 / 5.2 / 5.1Hurt
use Where2Act-style exploration instead of the similarity module (ablation)Where2Explore · Novel categories, pushing and pullingF-score: 24.8 / 25.2 / 30.2; 6.8 / 6.7 / 8.4Hurt
use Where2Act-style exploration instead of the similarity module (ablation)Where2Explore · Novel categories, pushing and pullingSample successful rate: 15.0 / 19.2 / 25.5; 5.4 / 6.2 / 5.3Hurt
remove few-shot exploration (ablation)Where2Explore · Novel categoriesF-score: 20.6; 3.9Hurt
train on all categories with abundant data (ablation)Where2Explore · Novel categoriesF-score: 47.9; 27.1Improved
use similarity-guided few-shot exploration rather than abundant full-category training (ablation)Where2Explore · Novel categoriesSample successful rate: 39.5 vs 40.3; 14.9 vs 13.9Mixed

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