AI Paper Atlas

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

Leverage Interactive Affinity for Affordance Learning

Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, Dacheng Tao

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 15 citations (OpenAlex)

Read the paper

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 interactive-affinity learning with IFE and KHPAffordance learning · CAL SeenKLD: 1.198 -> 0.965Improved
Use interactive-affinity learning with IFE and KHPAffordance learning · CAL UnseenKLD: 3.016 -> 2.823Improved
Add IFE and KHP rather than using neither (ablation)Pose-aided interactive affinity learning · CAL SeenKLD: 1.208 -> 0.965Improved
Add IFE and KHP rather than using neither (ablation)Pose-aided interactive affinity learning · CAL UnseenKLD: 5.593 -> 2.823Improved
Add KHP to IFE (ablation)Pose-aided interactive affinity learning · CAL SeenKLD: 1.126 -> 0.965Improved
Add KHP to IFE (ablation)Pose-aided interactive affinity learning · CAL UnseenKLD: 4.558 -> 2.823Improved
Add IFE to KHP (ablation)Pose-aided interactive affinity learning · CAL SeenKLD: 1.164 -> 0.965Improved
Add IFE to KHP (ablation)Pose-aided interactive affinity learning · CAL UnseenKLD: 3.576 -> 2.823Improved
Use separate body-part keypoint features instead of GAP pose features (ablation)KHP scheme · CAL SeenKLD: 1.317 -> 1.169Improved
Use separate body-part keypoint features instead of GAP pose features (ablation)KHP scheme · CAL UnseenKLD: 4.053 -> 3.933Improved
Use cross-transformer fusion instead of convolutional fusion with separate part features (ablation)KHP scheme · CAL SeenKLD: 1.169 -> 0.965Improved
Use cross-transformer fusion instead of convolutional fusion with separate part features (ablation)KHP scheme · CAL UnseenKLD: 3.933 -> 2.823Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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