AI Paper Atlas

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

Model-Agnostic Gender Debiased Image Captioning

Yusuke Hirota, Yuta Nakashima, Noa Garcia

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning · 10 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
Apply LIBRA to captioning modelsUpDn, OSCAR, and GRIT · MSCOCO validationLIC: UpDn 4.7 -> 1.5; OSCAR 2.4 -> 0.3; GRIT 3.1 -> 0.7Improved
Apply LIBRA to captioning modelsUpDn, OSCAR, and GRIT · MSCOCO validationError: UpDn 5.6 -> 4.5; OSCAR 3.0 -> 4.6; GRIT 3.5 -> 4.1Mixed
Apply LIBRA to captioning modelsUpDn, OSCAR, and GRIT · MSCOCO validationBiasAmp: UpDn 1.46 -> -2.23; OSCAR 1.78 -> -1.95; GRIT 3.05 -> 1.57Improved
Apply LIBRA instead of Gender equalizerNIC+ · MSCOCO validationLIC: NIC+ 1.4; Equalizer 6.8; LIBRA 0.4Improved
Apply LIBRA instead of Gender equalizerNIC+ · MSCOCO validationError: NIC+ 14.6; Equalizer 7.8; LIBRA 5.1Improved
Use T5 and Merged synthetic captions rather than Swap and T5 captions (ablation)LIBRA on UpDn · MSCOCO validationError: 6.2 -> 4.5Improved
Use T5 and Merged synthetic captions rather than Swap and T5 captions (ablation)LIBRA on OSCAR · MSCOCO validationError: 6.8 -> 4.6Improved
Train on all synthetic-caption types rather than T5 and Merged (ablation)LIBRA on UpDn · MSCOCO validationLIC: 1.5 -> 1.1Improved
Train on all synthetic-caption types rather than T5 and Merged (ablation)LIBRA on OSCAR · MSCOCO validationLIC: 0.3 -> 0Improved
Train DCG using BCS-biased captions instead of random perturbations (ablation)LIBRA on UpDn and OSCAR · MSCOCO validationLIC and Error: UpDn LIC 2.2 -> 1.5, Error 5.9 -> 4.5; OSCAR LIC 2.0 -> 0.3, Error 5.6 -> 4.6Improved
Apply LIBRA to captioning modelsNIC, SAT, FC, Att2in, UpDn, Transformer, OSCAR, ClipCap, and GRIT · MSCOCO validationCLIPScoreMixed
Apply LIBRA to captioning modelscaptioning models evaluated with reference-based metrics · MSCOCO validationBLEU-4: 79.6 -> 47.5Mixed

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