paper-with-me

홈 › Papers

Better Generalization with On-the-fly Dataset Denoising

2019-05-01 · ICLR 2019 5 · Jiaming Song, Tengyu Ma, Michael Auli, Yann Dauphin

Memorization in over-parameterized neural networks can severely hurt generalization in the presence of mislabeled examples. However, mislabeled examples are to hard avoid in extremely large datasets. We address this problem using the implicit regularization effect of stochastic gradient descent with large learning rates, which we find to be able to separate clean and mislabeled examples with remarkable success using loss statistics. We leverage this to identify and on-the-fly discard mislabeled examples using a threshold on their losses. This leads to On-the-fly Data Denoising (ODD), a simple yet effective algorithm that is robust to mislabeled examples, while introducing almost zero computational overhead. Empirical results demonstrate the effectiveness of ODD on several datasets containing artificial and real-world mislabeled examples.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingMemorization

Similar Papers 제목 키워드 기반

Denoising after Entropy-based Debiasing A Robust Training Method for Dataset Bias with Noisy Labels

2022-12-01 · Sumyeong Ahn, Se-Young Yun

Improperly constructed datasets can result in inaccurate inferences. For instance, models trained on biased datasets perform poorly in terms of generalization (i.e., dataset bias). Recent debiasing techniques have succes…

Denoising

WINNet: Wavelet-inspired Invertible Network for Image Denoising

2021-09-14 · Jun-Jie Huang, Pier Luigi Dragotti

Image denoising aims to restore a clean image from an observed noisy image. The model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretabilit…

DeblurringDenoisingImage DeblurringImage Denoising+1

Masked Image Training for Generalizable Deep Image Denoising

2023-03-23 · CVPR 2023 1 · Haoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid 외

When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the …

Deep LearningDenoisingImage Denoising

Learning to Drop: Robust Graph Neural Network via Topological Denoising

2020-11-13 · Dongsheng Luo, Wei Cheng, Wenchao Yu, Bo Zong 외

Graph Neural Networks (GNNs) have shown to be powerful tools for graph analytics. The key idea is to recursively propagate and aggregate information along edges of the given graph. Despite their success, however, the exi…

DenoisingGraph Neural NetworkLink PredictionNode Classification

CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization

2023-04-04 · Qi Gao, Zilong Li, Junping Zhang, Yi Zhang 외

Low-dose computed tomography (CT) images suffer from noise and artifacts due to photon starvation and electronic noise. Recently, some works have attempted to use diffusion models to address the over-smoothness and train…

Computed Tomography (CT)DenoisingOne-Shot Learning