paper-with-me

홈 › Papers

Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting

2026-04-22 · Alexander Weers, Daniel Rueckert, Martin J. Menten arxiv

Training vision-language models (VLMs) for medical report generation is often hindered by the scarcity of high-quality annotated data. This work evaluates the use of a weighted loss function to improve data efficiency. Compared to standard cross-entropy loss, which treats all token prediction errors equally, the reweighted loss shifts the focus to semantically salient tokens with outsized clinical importance. In experiments on ophthalmological report generation, we show that this simple method improves efficiency across multiple data scales, achieving similar report quality with up to ten times less training data.

📄 PDF Abstract BibTeX arXiv:2604.21082

Code (0)

등록된 구현이 없습니다.

Tasks

Medical Report Generation

Similar Papers 제목 키워드 기반

IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters

2019-03-28 · Xinshao Wang, Yang Hua, Elyor Kodirov, Neil M. Robertson

In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i.e., gradient magnitude with respect to logits, an angle that is no…

image-classificationImage ClassificationVideo Retrieval

Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification

2021-05-25 · S. Shi, Kai Qiao, Shuai Yang, L. Wang 외

The Graph Neural Network (GNN) has been widely used for graph data representation. However, the existing researches only consider the ideal balanced dataset, and the imbalanced dataset is rarely considered. Traditional m…

Ensemble LearningGraph Neural NetworkNode ClassificationTransfer Learning

What Matters to You? Towards Visual Representation Alignment for Robot Learning

2023-10-11 · Ran Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik 외

When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representa…

Zero-shot Generalization

Binary Classification: Is Boosting stronger than Bagging?

2024-10-24 · Dimitris Bertsimas, Vasiliki Stoumpou

Random Forests have been one of the most popular bagging methods in the past few decades, especially due to their success at handling tabular datasets. They have been extensively studied and compared to boosting models, …

Binary ClassificationClassification

Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection

2022-06-28 · Pinhao Song, Pengteng Li, Linhui Dai, Tao Wang 외

Complicated underwater environments bring new challenges to object detection, such as unbalanced light conditions, low contrast, occlusion, and mimicry of aquatic organisms. Under these circumstances, the objects capture…

Objectobject-detectionObject DetectionRegion Proposal