AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Order Learning Using Partially Ordered Data via Chainization

Seon-Ho Lee, Chang-Su Kim

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Statistical alignment and hypothesis testing · 9 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
fine-tune comparator on chainization pseudo pairs (vs OL)order learning comparator · Adience, gamma=0.005%accuracy: 31.8% -> 56.7%Improved
fine-tune comparator on chainization pseudo pairs (vs OL)order learning comparator · MORPH II linear extension, gamma=0.05%Spearman rho: 0.897 -> 0.918Improved
fine-tune comparator on chainization pseudo pairs (vs OL)order learning comparator · Adience linear extension, gamma=0.01%Spearman rho: 0.809 -> 0.908Improved
fine-tune comparator on chainization pseudo pairs (vs OL)order learning comparator · Aesthetics linear extension, gamma=0.01%Spearman rho: 0.665 -> 0.838Improved
estimate missing orderings with comparator (vs Kahn topological sort)Kahn's algorithm · MORPH II linear extension, gamma=0.05%Spearman rho: 0.205 -> 0.918Improved
apply chainization with partial supervision (gamma=0.03%) vs full supervisionorder learning on Adience · Adienceaccuracy: 61.7 -> 59.7Hurt
use chainization at gamma=0.08% vs POEPOE · Adienceaccuracy: 60.5 -> 60.5No clear effect
add chainization to OL for domain adaptationOL · Adience to MORPH IIaccuracy: 43.8 -> 51.5Improved
add chainization to OL for domain adaptationOL · Adience to MORPH IISpearman rho: 0.630 -> 0.798Improved
use chainization in bipartite case vs OLOL · MORPH II bipartiteMAE: 8.696 -> 5.903Improved
use chainization in bipartite case vs OLOL · Adience bipartiteMAE: 1.682 -> 0.807Improved
use chainization in bipartite case vs OLOL · MORPH II bipartiteSpearman rho: 0.068 -> 0.638Improved

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