AI Paper Atlas

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

Reasoning About Fine-Grained Attribute Phrases Using Reference Games

Jong-Chyi Su, Chenyun Wu, Huaizu Jiang, Subhransu Maji

ICCV 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 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
train speaker on contrastive pairs (discerning speaker) instead of single image (ablation)speaker · Reference game (SL listener, top-5)accuracy (%): 80.6 -> 91.4Improved
train speaker on contrastive pairs (discerning speaker) instead of single image (ablation)speaker · Reference game (human listener, top-5, Test*)accuracy (%): 64.2 -> 80.2Improved
rerank simple speaker outputs with listener SL_rsimple speaker · Reference game (human listener, top-5)accuracy (%): 64.2 -> 82.6Improved
rerank discerning speaker outputs with listener SL_rdiscerning speaker · Reference game (human listener, top-5)accuracy (%): 80.2 -> 90.0Improved
rerank with contrastive listener SL instead of SL_r (ablation)pragmatic simple speaker · Reference game (human listener, top-5)accuracy (%): 82.6 -> 80.8Hurt
train listener on contrastive data (SL vs SL_r) (ablation)simple listener · Reference game, human phrases (test)accuracy (%): 84.2 -> 86.3Improved
interpret both phrases at once (DL) instead of averaging two simple listeners (ablation)listener · Reference game, human phrases (test)accuracy (%): 89.3 -> 88.9No clear effect
use first-listed attribute instead of later ones (ablation)simple listener SL · Reference game (test)accuracy (%): 81.6 -> 92.3Improved
use attribute phrases (same number, 46) instead of OID attributesimage embedding · FGVC-aircraft classificationaccuracy: 12% betterImproved
increase to 300 attribute phrasesimage embedding · FGVC-aircraft classificationaccuracy: 32%, about 20% better than OIDImproved
use opponent attribute space (phrase pairs) instead of single phrasesimage embedding · FGVC-aircraft classificationaccuracyNo clear effect
use contrastive SL_r vs SL listener for embedding (ablation)image embedding · FGVC-aircraft classificationaccuracyNo 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