AI Paper Atlas

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

Combining Task Predictors via Enhancing Joint Predictability

Kwang In Kim, Christian Richardt, Hyung Jin Chang

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 0 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 joint denoising of references along with the target (ablation)NPC · OSR attribute rankingaccuracy improvement over f0: 1.96 -> 2.13Improved
add automatic relevance determination (ablation)NPC · OSR attribute rankingaccuracy improvement over f0: 1.88 -> 2.13Improved
use nonlinear instead of linear combination (XOR target)LPC to NPC · Toy problem 2accuracy: 74.24 -> 100Improved
use joint (linear) relevance instead of pairwiseOPC to LPC · Toy problem 1accuracy: 67.24 -> 100Improved
use NPC instead of OPCpredictor combination · Shoes classificationaccuracy (%): 58.52 -> 62.87Improved
use NPC instead of OPCpredictor combination · Pubfig classificationaccuracy (%): 82.55 -> 86.51Improved
use NPC instead of OPCpredictor combination · OSR classificationaccuracy (%): 77.16 -> 79.71Improved
use NPC instead of OPCpredictor combination · aPascal classificationaccuracy (%): 39.77 -> 40.34Improved
use NPC instead of OPCpredictor combination · CUB classificationaccuracy (%): 67.75 -> 68.26Improved
raise number of basis vectors N' from 300 to 1,000 (ablation)NPC · low-rank GP approximationaccuracyNo clear effect
use NPC on AWA2 versus OPC and MTLpredictor combination · AWA2 ranking (80 attributes)attributes with significant gain: 74 vs 8 and 33Improved
use NPC on Zap50KNPC · Zap50K rankingsignificant gains: 0 significantly better, 4 on parNo clear effect

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