AI Paper Atlas

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

Learn on Source, Refine on Target: A Model Transfer Learning Framework with Random Forests

Noam Segev, Maayan Harel, Shie Mannor, Koby Crammer, Ran El‐Yaniv

TPAMI 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 148 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
Combine STRUT and SER forests into MIX (union, 100 trees)SER · lettererror rate (%): 18.9 -> 16.7Improved
Combine STRUT and SER forests into MIXSTRUT · lettererror rate (%): 21.0 -> 16.7Improved
Combine STRUT and SER forests into MIXSER · digitserror rate (%): 2.9 -> 3.8Hurt
Combine STRUT and SER forests into MIXSTRUT · Activity (median)error rate (%): 14.6 -> 13.8Improved
Combine STRUT and SER into MIX when STRUT is poorSER · inversion (1%)error rate (%): 58.5 -> 44.1Mixed
Combine STRUT and SER into MIX when SER is poorSER · inversion (5%)error rate (%): 36.5 -> 22.2Improved
Combine STRUT and SER into MIXSTRUT · high-res (5%)error rate (%): 28.3 -> 21.8Improved
Use 100 trees instead of 50 for STRUT and SER (ablation)STRUT and SER · all datasetserror rate (%)No clear effect
MIX (STRUT+SER) vs STRUT alone on moving sourceSTRUT · Toy moving sourcetest error: 6.1 -> 6.4Mixed
MIX vs SER alone on mixed boxesSER · Toy mixed boxestest error: 6.6 -> 5.5Improved
Use MIX instead of TradaBoost (instance transfer)TradaBoost · lettererror rate (%): 41.7 -> 16.7Improved
Use MIX instead of TrBagg (instance transfer)TrBagg · lettererror rate (%): 29.3 -> 16.7Improved

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