A Gradient-based Approach for Online Robust Deep Neural Network Training with Noisy Labels
원문 초록
Learning with noisy labels is an important topic for scalable training in many real-world scenarios. However, few previous research considers this problem in the online setting, where the arrival of data is streaming. In this paper, we propose a novel gradient-based approach to enable the detection of noisy labels for the online learning of model parameters, named Online Gradient-based Robust Selection (OGRS). In contrast to the previous sample selection approach for the offline training that requires the estimation of a clean ratio of the dataset before each epoch of training, OGRS can automatically select clean samples by steps of gradient update from datasets with varying clean ratios without changing the parameter setting. During the training process, the OGRS method selects clean samples at each iteration and feeds the selected sample to incrementally update the model parameters. We provide a detailed theoretical analysis to demonstrate data selection process is converging to the low-loss region of the sample space, by introducing and proving the sub-linear local Lagrangian regret of the non-convex constrained optimization problem. Experimental results show that it outperforms state-of-the-art methods in different settings.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sfumato Supervision: Learning Instance Segmentation with Noisy Labels
On the Role of Label Noise in the Feature Learning Process
Detect and Correct: A Selective Noise Correction Method for Learning with Noisy Labels
Exploring Video-Based Driver Activity Recognition under Noisy Labels
Early Stopping Against Label Noise Without Validation Data
Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space
토론
이 논문과 연결된 포럼 글이 아직 없습니다.