CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification

TL;DR

This paper introduces CICA, a novel framework that enhances CLIP's zero-shot document image classification by leveraging document-specific textual information, achieving significant accuracy improvements with minimal additional parameters.

Contribution

We propose CICA, a content-injected contrastive alignment framework that improves zero-shot document image classification by incorporating a new content module and a coupled-contrastive loss.

Findings

CICA improves CLIP's ZSL top-1 accuracy by 6.7%.

CICA increases GZSL harmonic mean by 24%.

The module adds only 3.3% more parameters to CLIP.

Abstract

Zero-shot learning has been extensively investigated in the broader field of visual recognition, attracting significant interest recently. However, the current work on zero-shot learning in document image classification remains scarce. The existing studies either focus exclusively on zero-shot inference, or their evaluation does not align with the established criteria of zero-shot evaluation in the visual recognition domain. We provide a comprehensive document image classification analysis in Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) settings to address this gap. Our methodology and evaluation align with the established practices of this domain. Additionally, we propose zero-shot splits for the RVL-CDIP dataset. Furthermore, we introduce CICA (pronounced 'ki-ka'), a framework that enhances the zero-shot learning capabilities of CLIP. CICA consists of a novel 'content module' designed to leverage any generic document-related textual information. The discriminative features extracted by this module are aligned with CLIP's text and image features using a novel 'coupled-contrastive' loss. Our module improves CLIP's ZSL top-1 accuracy by 6.7% and GZSL harmonic mean by 24% on the RVL-CDIP dataset. Our module is lightweight and adds only 3.3% more parameters to CLIP. Our work sets the direction for future research in zero-shot document classification.