paper-with-me

Papers

Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents

2022-10-11 · Muhammad Khalifa, Yogarshi Vyas, Shuai Wang, Graham Horwood, Sunil Mallya, Miguel Ballesteros

We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments where new document categories could potentially emerge. We focus exclusively on the zero-shot setting where inference is done on new unseen classes. To address this task, we propose a matching-based approach that relies on a pairwise contrastive objective for both pretraining and fine-tuning. Our results show a significant boost in Macro F$_1$ from the proposed pretraining step in both supervised and unsupervised zero-shot settings.

📄 PDF Abstract BibTeX arXiv:2210.05613

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDocument Classificationzero-shot-classificationZero-Shot Learning

Similar Papers 제목 키워드 기반

PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification

2023-05-24 · Yau-Shian Wang, Ta-Chung Chi, Ruohong Zhang, Yiming Yang

We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural text matching problem where each documen…

ClassificationContrastive Learningtext-classificationText Classification+2

Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders

2022-12-14 · Jongseong Jang, Daeun Kyung, Seung Hwan Kim, Honglak Lee 외

Deep neural networks are increasingly used in medical imaging for tasks such as pathological classification, but they face challenges due to the scarcity of high-quality, expert-labeled training data. Recent efforts have…

ClassificationContrastive LearningSentencezero-shot-classification+1

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

2025-03-03 · Junhyun Park, Chanyu Moon, Donghwan Lee, KyungSu Kim 외

Contrastive Language-Image Pre-Training (CLIP) has enabled zero-shot classification in radiology, reducing reliance on manual annotations. However, conventional contrastive learning struggles with normal case detection d…

Anomaly LocalizationClassificationClusteringContrastive Learning+3

Modeling Caption Diversity in Contrastive Vision-Language Pretraining

2024-04-30 · Samuel Lavoie, Polina Kirichenko, Mark Ibrahim, Mahmoud Assran 외

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent t…

Diversityzero-shot-classificationZero-Shot Learning

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

2024-05-06 · Sankalp Sinha, Muhammad Saif Ullah Khan, Talha Uddin Sheikh, Didier Stricker 외

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 …

Document Classificationdocument-image-classificationDocument Image ClassificationGeneralized Zero-Shot Learning+3