AI Paper Atlas

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

FLEX: Faithful Linguistic Explanations for Neural Net Based Model Decisions

Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 14 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 relevance vector and relevance loss to FLEX (ablation)FLEX · CUBDREL: 16.48 -> 17.85Improved
add relevance vector and relevance loss to FLEX (ablation)FLEX · MPIIDREL: 14.13 -> 16.11Improved
add weighted CNN features to baseline captioner (ablation)Baseline · CUBDREL: 13.67 -> 16.48Improved
add weighted CNN features to baseline captioner (ablation)Baseline · MPIIDREL: 13.48 -> 14.13Improved
vary relevance loss weight lambda from 0 to 0.1 (ablation)FLEX · CUBDREL: 16.48 -> 17.85Improved
use FLEX instead of GVE on CUBexplanation generator · CUBDREL: 15.67 -> 17.85Improved
use FLEX instead of MME on MPIIexplanation generator · MPIIBLEU-4: 19.88 -> 19.11Hurt
use FLEX instead of GVE on CUBexplanation generator · CUBBLEU-4: 28.43 -> 30.16Improved
use FLEX instead of GVE/MME for unseen classesexplanation generator · CUB unseen classesDREL: 32.35 -> 36.72Improved

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