X-ray transferable polyrepresentation learning

2025/07/07 by Weronika Hryniewska-Guzik, Hryniewska-Guzik, Weronika, Przemysław Biecek +1
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2507.06264

openalex publication_date 2025/07/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The success of machine learning algorithms is inherently related to the extraction of meaningful features, as they play a pivotal role in the performance of these algorithms. Central to this challenge is the quality of data representation. However, the ability to generalize and extract these features effectively from unseen datasets is also crucial. In light of this, we introduce a novel concept: the polyrepresentation. Polyrepresentation integrates multiple representations of the same modality extracted from distinct sources, for example, vector embeddings from the Siamese Network, self-supervised models, and interpretable radiomic features. This approach yields better performance metrics compared to relying on a single representation. Additionally, in the context of X-ray images, we demonstrate the transferability of the created polyrepresentation to a smaller dataset, underscoring its potential as a pragmatic and resource-efficient approach in various image-related solutions. It is worth noting that the concept of polyprepresentation on the example of medical data can also be applied to other domains, showcasing its versatility and broad potential impact.

Citations

• DINOv2: Learning Robust Visual Features without Supervision
• Chest X-Ray Bone Suppression for Improving Classification of\n Tuberculosis-Consistent Findings
• Training data-efficient image transformers & distillation through attention
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Evaluating Multimodal Representations on Visual Semantic Textual Similarity
• A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
• Improving Prognostic Performance in Resectable Pancreatic Ductal Adenocarcinoma using Radiomics and Deep Learning Features Fusion in CT Images
• Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with\n Application to TB Detection on a Small-Scale Dataset
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Searching for MobileNetV3
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Word Mover's Embedding: From Word2Vec to Document Embedding
• Repeatability of Multiparametric Prostate MRI Radiomics Features
• Computational Radiomics System to Decode the Radiographic Phenotype
• Densely Connected Convolutional Networks
• Representation Learning: A Review and New Perspectives
• Representation Learning: A Review and New Perspectives
• A Survey on Transfer Learning

Related

• Synthetic Privileged Information Enhances Medical Image Representation Learning
• Imbalance-Aware Self-Supervised Learning for 3D Radiomic Representations
• Multi-domain improves out-of-distribution and data-limited scenarios for medical image analysis
• MoCo-Transfer: Investigating out-of-distribution contrastive learning for limited-data domains
• StyleX: A Trainable Metric for X-ray Style Distances