Weighting What Matters: Boosting Sample Efficiency in Medical Report Generation via Token Reweighting
For medical VLM training with limited annotated data, this simple reweighting method significantly boosts sample efficiency.
This work introduces a token reweighting loss for medical report generation that prioritizes clinically important tokens, achieving comparable report quality with up to 10x less training data.
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.