paper-with-me

Papers

PRIOR: Prototype Representation Joint Learning from Medical Images and Reports

2023-07-24 · ICCV 2023 1 · Pujin Cheng, Li Lin, Junyan Lyu, Yijin Huang, Wenhan Luo, Xiaoying Tang

Contrastive learning based vision-language joint pre-training has emerged as a successful representation learning strategy. In this paper, we present a prototype representation learning framework incorporating both global and local alignment between medical images and reports. In contrast to standard global multi-modality alignment methods, we employ a local alignment module for fine-grained representation. Furthermore, a cross-modality conditional reconstruction module is designed to interchange information across modalities in the training phase by reconstructing masked images and reports. For reconstructing long reports, a sentence-wise prototype memory bank is constructed, enabling the network to focus on low-level localized visual and high-level clinical linguistic features. Additionally, a non-auto-regressive generation paradigm is proposed for reconstructing non-sequential reports. Experimental results on five downstream tasks, including supervised classification, zero-shot classification, image-to-text retrieval, semantic segmentation, and object detection, show the proposed method outperforms other state-of-the-art methods across multiple datasets and under different dataset size settings. The code is available at https://github.com/QtacierP/PRIOR.

📄 PDF Abstract BibTeX arXiv:2307.12577

Code (1)

qtacierp/prior 공식 구현 pytorch

Tasks

Contrastive LearningImage to textImage-to-Text Retrievalobject-detectionObject DetectionRepresentation LearningRetrievalSemantic SegmentationSentenceText Retrievalzero-shot-classificationZero-Shot Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Diverse Normal Prototypes-Guided Contrastive Reconstruction for Medical Anomaly Detection

2025-08-27 · Luhu Li, Bin Liu, Bowen Lin, Zihan Shen 외 arxiv

Anomaly detection in medical images is challenging due to limited annotations and the domain gap. Existing reconstruction-based methods often rely on frozen pre-trained encoders, restricting adaptation to domain-specific…

Representation LearningAnomaly Detection

Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation

2021-11-22 · Huimin Wu, Xiaomeng Li, Kwang-Ting Cheng

This paper presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervis…

Contrastive LearningImage SegmentationMedical Image SegmentationRepresentation Learning+4

Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation

2022-03-19 · Cheng Bian, Chenglang Yuan, Kai Ma, Shuang Yu 외

Due to the lack of properly annotated medical data, exploring the generalization capability of the deep model is becoming a public concern. Zero-shot learning (ZSL) has emerged in recent years to equip the deep model wit…

Domain AdaptationImage SegmentationMedical Image SegmentationRelation+2

FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection

2025-10-10 · Shubham Trehan, Udhav Ramachandran, Akash Rao, Ruth Scimeca 외 arxiv

Object detection in biomedical settings is fundamentally constrained by the scarcity of labeled data and the frequent emergence of novel or rare categories. We present FSP-DETR, a unified detection framework that enables…

Object Detection

Efficient Prototype Consistency Learning in Medical Image Segmentation via Joint Uncertainty and Data Augmentation

2025-05-22 · Lijian Li, Yuanpeng He, Chi-Man Pun

Recently, prototype learning has emerged in semi-supervised medical image segmentation and achieved remarkable performance. However, the scarcity of labeled data limits the expressiveness of prototypes in previous method…

Data AugmentationImage SegmentationMedical Image SegmentationSemantic Segmentation+2