AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Learning to Evaluate Image Captioning

Yin Cui, Guandao Yang, Andreas Veit, Xun Huang, Serge Belongie

CVPR 2018 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 139 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 pathological data augmentation during training (ablation)Learned caption metric · COCO validation M1Pearson's ρ: 0.821 -> 0.939Improved
Add pathological data augmentation during training (ablation)Learned caption metric · COCO validation M2Pearson's ρ: 0.807 -> 0.949Improved
Include image features in the critique context (ablation)Learned caption metric · COCO validationhuman-versus-generated caption discriminationImproved
Add a reference caption to image-only context (ablation)Learned caption metric · COCO validationhuman-versus-generated caption discriminationNo clear effect
Train without data sampling or augmentation (ablation)Learned caption metric · Random-caption, random-word, and word-permutation robustness testsrobustness scoreHurt
Use a linear classifier with concatenated context and candidate features instead of nonlinear interactions (ablation)Learned caption metric with data augmentation · Random-caption robustness testrobustnessHurt
Increase LSTM layers or hidden-feature size (ablation)Learned caption metric · Capability evaluationdiscrimination performanceNo clear effect
Use data augmentation rather than training without it (ablation)Learned caption metric · COCO validation M4 detailnessPearson's ρ: 0.844 -> 0.626Hurt
Use data augmentation rather than training without it (ablation)Learned caption metric · COCO validation M3 correctnessPearson's ρ: 0.430 -> 0.720Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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