AI Paper Atlas

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

Grounding Visual Explanations

Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Post-hoc explanation analysis · 183 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 phrase-critic reranking to explanation samplingexplanation model · CUB human evaluation% correct noun phrases: 76.64 -> 77.96Improved
add phrase-critic reranking to explanation samplingexplanation model · CUB human evaluation% correct sentences: 52.10 -> 61.97Improved
use phrase-critic instead of grounding-model score averaginggrounding model · CUB human evaluation% correct noun phrases: 76.32 -> 77.96Improved
use phrase-critic instead of grounding-model score averaginggrounding model · CUB human evaluation% correct sentences: 49.85 -> 61.97Improved
use grounding model averaging instead of fluency-only baselineexplanation model · CUB human evaluation% correct sentences: 52.10 -> 49.85Hurt
show bounding boxes with explanations (ablation)Phrase Critic · CUB MTurk informativenessshare more informative: 41.9% more informative, 49.3% equally informativeImproved
add phrase-critic on top of grounding modelgrounding model · CUB head regionEuclidean distance (lower better): 46.31 -> 20.26Improved
add phrase-critic on top of grounding modelgrounding model · CUB eye region% accuracy: 60.78 -> 56.72Hurt
add phrase-critic on top of grounding modelgrounding model · CUB head region% accuracy: 60.60 -> 74.06Improved
use phrase-critic instead of grounding modelgrounding model · FOIL classificationaccuracy: 56.68 -> 87.00Improved
use phrase-critic instead of grounding modelgrounding model · FOIL word detectionaccuracy: 39.80 -> 73.72Improved
use phrase-critic instead of grounding modelgrounding model · FOIL word correctionaccuracy: 8.80 -> 49.60Improved

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