AI Paper Atlas

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

An Easy-to-hard Learning Paradigm for Multiple Classes and Multiple Labels

Weiwei Liu, Ivor W. Tsang, Klaus-Robert Müller

JMLR 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 78 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 easy-to-hard class chaining (CCMC) to OVROVR · KTHtesting error (%): 8.18 -> 7.34Improved
optimize class order with greedy search (ablation)CCMC · KTHtesting error (%): 7.34 -> 6.29Improved
optimize class order with dynamic programming (ablation)CCMC-Greedy · KTHtesting error (%): 6.29 -> 5.66Improved
add class chaining with DP ordering to OVROVR · IRIStesting error (%): 10.00 -> 3.33Improved
add class chaining with DP ordering to OVROVR · RCV1testing error (%): 11.90 -> 11.68Improved
add class chaining with DP ordering to OVR with background dataOVR · SOWERBYtesting error (%): 18.03 -> 15.24Improved
increase fast-greedy parameter w from 10 to 100 (ablation)CCMC-FG · ALOItesting error (%): 5.27 -> 4.78Improved
increase fast-greedy parameter w from 10 to 100 (ablation)CCMC-FG · ALOItraining time (s): 16,327s -> 163,891sHurt
use CCMC-DP instead of OVROVR · RCV1training time (s): 18.16s -> 16,450.55sHurt
add CCMC-FG on ResNet-34 features, w=50ResNet-34 · ILSVRC2012 subsettesting error (%): 21.51 -> 19.84Improved
add CCMC-FG on VGG features, w=10VGG · ILSVRC2012 subsettesting error (%): 23.95 -> 23.98No clear effect
increase w from 10 to 50 for CCMC-FG on VGG features (ablation)CCMC-FG+VGG · ILSVRC2012 subsettesting error (%): 23.98 -> 20.73Improved

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