AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Contrastive Language-Image Pre-Training with Knowledge Graphs

Xuran Pan, Tianzhu Ye, Dongchen Han, Shiji Song, Gao Huang

NeurIPS 2022 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 24 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 knowledge-graph pretraining and multimodal fusion to CLIPCLIP ViT-L/14 · VQA test-devaccuracy: 74.10 -> 76.11Improved
Add knowledge-graph pretraining and multimodal fusion to CLIPCLIP ViT-L/14 · Flickr30K text retrievalR@1: 88.6 -> 89.2Improved
Add knowledge-graph pretraining and multimodal fusion to CLIPCLIP ViT-L/14 · ImageNetaccuracy (%): 84.2 -> 84.4Improved
Add knowledge-graph pretraining and multimodal fusion to CLIPCLIP ViT-L/14 · GLUE MNLIaccuracy: 80.9 -> 83.6Improved
Train CLIP on knowledge data without graph-based objectives (ablation)CLIP ViT-B/32 · Flickr30K retrievalText R@1: 84.2 -> 84.5No clear effect
Add the E2E entity-entity objective (ablation)Knowledge-CLIP · Flickr30K retrievalText R@1: 85.0 -> 86.3Improved
Add the E2R entity-relation objective (ablation)Knowledge-CLIP · Flickr30K retrievalText R@1: 85.7 -> 86.3Improved
Add the G2E graph-entity objective (ablation)Knowledge-CLIP · Flickr30K retrievalText R@1: 84.9 -> 86.3Improved
Add the knowledge-distillation loss (ablation)Knowledge-CLIP · Flickr30K retrievalText R@1: 82.4 -> 86.3Improved
Add the knowledge-distillation loss (ablation)Knowledge-CLIP · Flickr30K retrievalImage R@1: 62.5 -> 67.2Improved
Use Knowledge-CLIP instead of CLIP on negation questionsCLIP · VQA Negationaccuracy: 64.7 -> 66.8 (+2.1)Improved
Use Knowledge-CLIP instead of CLIP on color questionsCLIP · VQA Coloraccuracy: 54.2 -> 59.9 (+5.7)Improved

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