AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Merge or Not? Learning to Group Faces via Imitation Learning

Yue He, Kaidi Cao, Cheng Li, Chen Loy

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 19 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
add imitation-learned sequential merge decisions to hierarchical clusteringHC · LFW-AlbumF1 (%): 76.6 -> 91.1Improved
add imitation-learned sequential merge decisions to hierarchical clusteringHC · ACCIO-1F1 (%): 28.9 -> 84.3Improved
add imitation-learned sequential merge decisions to graph degree linkageGDL · GFWF1 (%): 55.9 -> 74.5Improved
add face quality feature (ablation)IL-HC · LFW-AlbumF1 (%): 89.5 -> 91.1Improved
add face quality feature (ablation)IL-HC · ACCIO-1F1 (%): 65.0 -> 84.3Improved
add face quality feature (ablation)IL-HC · GFWF1 (%): 48.4 -> 67.3Improved
add long-term operation-cost reward (ablation)IL-HC · LFW-AlbumF1 (%): 90.7 -> 91.1Improved
add long-term operation-cost reward (ablation)IL-HC · GFWF1 (%): 62.6 -> 67.3Improved
use the learned short-term reward instead of a naive ±1 ground-truth reward (ablation)IL-HC · LFW-AlbumF1 (%): 73.0 -> 91.1Improved
use the learned short-term reward instead of a naive ±1 ground-truth reward (ablation)IL-HC · GFWF1 (%): 17.1 -> 67.3Improved
use an HC-based recommender rather than a random pair recommender (ablation)imitation-learning face grouping · GFWF1 (%): 61.9% (random recommender)Improved
choose candidate pairs exhaustively using the action-value function rather than using a clustering recommender (ablation)imitation-learning face grouping · GFWF1 (%): 82.7%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