paper-with-me

홈 › Papers

GradMask: Reduce Overfitting by Regularizing Saliency

2019-04-16 · Becks Simpson, Francis Dutil, Yoshua Bengio, Joseph Paul Cohen

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.

📄 PDF Abstract BibTeX arXiv:1904.07478

Code (0)

등록된 구현이 없습니다.

Tasks

Lesion Segmentation

Similar Papers 제목 키워드 기반

GradMask: Effective Fine-tuning on Large-scale Pretrained Language Models via Gradient Masking

2021-05-24 · Anonymous

Pretrained language models have dominated a variety of NLP tasks. However, fine-tuning large pretrained models on downstream tasks tend to achieve degenerated and unstable results, especially when there are only a limite…

GradMask: Gradient-Guided Token Masking for Textual Adversarial Example Detection

2021-11-16 · ACL ARR September 2021 9 · Anonymous

We present a simple model-agnostic textual adversarial example detection scheme called GradMask. It uses gradient signals to detect adversarially perturbed tokens in an input sequence and occludes such tokens by a maskin…

Regularizing CNNs with Locally Constrained Decorrelations

2016-11-07 · Pau Rodríguez, Jordi Gonzàlez, Guillem Cucurull, Josep M. Gonfaus 외

Regularization is key for deep learning since it allows training more complex models while keeping lower levels of overfitting. However, the most prevalent regularizations do not leverage all the capacity of the models s…

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

2019-07-25 · Lin Zehui, PengFei Liu, Luyao Huang, Junkun Chen 외

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurr…

Regularizing Trajectories to Mitigate Catastrophic Forgetting

2019-09-25 · Paul Michel, Elisabeth Salesky, Graham Neubig

Regularization-based continual learning approaches generally prevent catastrophic forgetting by augmenting the training loss with an auxiliary objective. However in most practical optimization scenarios with noisy data a…

Continual Learning