GradMask: Reduce Overfitting by Regularizing Saliency
원문 초록
With too few samples or too many model parameters, overfitting can inhibit the ability to generalise predictions to new data. Within medical imaging, this can occur when features are incorrectly assigned importance such as distinct hospital specific artifacts, leading to poor performance on a new dataset from a different institution without those features, which is undesirable. Most regularization methods do not explicitly penalize the incorrect association of these features to the target class and hence fail to address this issue. We propose a regularization method, GradMask, which penalizes saliency maps inferred from the classifier gradients when they are not consistent with the lesion segmentation. This prevents non-tumor related features to contribute to the classification of unhealthy samples. We demonstrate that this method can improve test accuracy between 1-3% compared to the baseline without GradMask, showing that it has an impact on reducing overfitting.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
How We Won the ISLES'24 Challenge by Preprocessing
HWA-UNETR: Hierarchical Window Aggregate UNETR for 3D Multimodal Gastric Lesion Segmentation
ZS-VCOS: Zero-Shot Outperforms Supervised Video Camouflaged Object Segmentation
STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation
Modality-Independent Brain Lesion Segmentation with Privacy-aware Continual Learning
Learning from spatially inhomogenous data: resolution-adaptive convolutions for multiple sclerosis lesion segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.