paper-with-me

홈 › Papers

Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels

2019-11-21 · ICML 2020 1 · Lu Jiang, Di Huang, Mason Liu, Weilong Yang

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This paper makes three contributions. First, we establish the first benchmark of controlled real-world label noise from the web. This new benchmark enables us to study the web label noise in a controlled setting for the first time. The second contribution is a simple but effective method to overcome both synthetic and real noisy labels. We show that our method achieves the best result on our dataset as well as on two public benchmarks (CIFAR and WebVision). Third, we conduct the largest study by far into understanding deep neural networks trained on noisy labels across different noise levels, noise types, network architectures, and training settings. The data and code are released at the following link: http://www.lujiang.info/cnlw.html

📄 PDF Abstract BibTeX arXiv:1911.09781

Code (3)

google-research/google-research/tree/master/mentormix 공식 구현 jax
MindCode-4/code-7/tree/main/Learning-with-Noisy-Labels mindspore
ljy-hy/mentormix_pytorch pytorch

Tasks

Deep LearningImage Classification

Similar Papers 제목 키워드 기반

Synthetic vs Real: Deep Learning on Controlled Noise

2019-09-25 · Lu Jiang, Di Huang, Weilong Yang

Performing controlled experiments on noisy data is essential in thoroughly understanding deep learning across a spectrum of noise levels. Due to the lack of suitable datasets, previous research have only examined deep le…

Deep Learning

NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing

2023-05-18 · Tingting Wu, Xiao Ding, Minji Tang, Hao Zhang 외

Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects of label noise, learning with noisy lab…

Learning with noisy labels

Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems

2021-06-16 · ACL ARR Jun 2021 6 · Anonymous

Emotion recognition models are a key component of several downstream applications, such as mental health assessments. These models are usually trained on small, clean, and synthetically controlled datasets, which leads t…

Data AugmentationEmotion Recognitionspeech-recognitionSpeech Recognition

Towards the Identifiability in Noisy Label Learning: A Multinomial Mixture Approach

2023-01-04 · Cuong Nguyen, Thanh-Toan Do, Gustavo Carneiro

Learning from noisy labels (LNL) plays a crucial role in deep learning. The most promising LNL methods rely on identifying clean-label samples from a dataset with noisy annotations. Such an identification is challenging …

Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance

2023-11-02 · Song Wang, Zhen Tan, Ruocheng Guo, Jundong Li

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios…