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

arXiv: https://arxiv.org/abs/2405.03660 · HTML: https://mlsanity.com/paper/2405.03660/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 6 May 2024.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild](https://mlsanity.com/paper/1605.04253/) (2016)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Generalized Zero-Shot Learning via Synthesized Examples](https://mlsanity.com/paper/1712.03878/) (2017)
- [Synthesized Classifiers for Zero-Shot Learning](https://mlsanity.com/paper/1603.00550/) (2016)
- [Open World Compositional Zero-Shot Learning](https://mlsanity.com/paper/2101.12609/) (2021)
- [A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts](https://mlsanity.com/paper/1712.01381/) (2017)
- [Transferable Contrastive Network for Generalized Zero-Shot Learning](https://mlsanity.com/paper/1908.05832/) (2019)
- [I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification](https://mlsanity.com/paper/2212.02291/) (2022)
- [Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification](https://mlsanity.com/paper/1704.03557/) (2017)
- [Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1801.09321/) (2018)
- [Modular Multimodal Architecture for Document Classification](https://mlsanity.com/paper/1912.04376/) (2019)
- [Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines](https://mlsanity.com/paper/1711.05862/) (2017)
- [Analysis of Convolutional Neural Networks for Document Image Classification](https://mlsanity.com/paper/1708.03273/) (2017)
- [Self-Supervised Representation Learning on Document Images](https://mlsanity.com/paper/2004.10605/) (2020)
- [Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents](https://mlsanity.com/paper/2210.05613/) (2022)
- [Human Pose Descriptions and Subject-Focused Attention for Improved Zero-Shot Transfer in Human-Centric Classification Tasks](https://mlsanity.com/paper/2403.06904/) (2024)

## Built on by (most cited first, 1 of 1)

- [CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities](https://mlsanity.com/paper/2512.11901/) (2025)

## Abstract (arXiv)

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.