AI Paper Atlas

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

Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models

Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu

AAAI 2023 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 2 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

add intra-modal contrastive loss · FUNSD · F1: 89.77 -> 90.45 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
use alignment-enriched tuning instead of LayoutLMv3 fine-tuningLayoutLMv3_base · FUNSDF1: 89.82 -> 91.55Improved
use alignment-enriched tuning instead of LayoutLMv3 fine-tuningLayoutLMv3_base · CORDF1: 95.97 -> 97.04Improved
use alignment-enriched tuning instead of LayoutLMv3 fine-tuningLayoutLMv3_base · DocVQAANLS: 78.76 -> 79.73Improved
add document-level image-text contrastive loss (ablation)AETNet_base with supervised objective · FUNSDF1: 89.77 -> 90.44Improved
add document-level image-text contrastive loss (ablation)AETNet_base with supervised objective · CORDF1: 96.30 -> 96.48Improved
add intra-modal contrastive loss (ablation)AETNet_base with supervised objective · FUNSDF1: 89.77 -> 90.45Improved
add intra-modal contrastive loss (ablation)AETNet_base with supervised objective · CORDF1: 96.30 -> 96.61Improved
add global-local image-text contrastive loss (ablation)AETNet_base with supervised objective · FUNSDF1: 89.77 -> 90.18Improved
add global-local image-text contrastive loss (ablation)AETNet_base with supervised objective · CORDF1: 96.30 -> 96.37Improved
add patch-level image-text alignment loss (ablation)AETNet_base with supervised objective · FUNSDF1: 89.77 -> 90.69Improved
add patch-level image-text alignment loss (ablation)AETNet_base with supervised objective · CORDF1: 96.30 -> 96.78Improved
add alignment losses and alignment-aware encoders rather than using only supervised tuning (ablation)LayoutLMv3_base on FUNSD · FUNSDF1: 89.82 -> 91.55Improved

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