paper-with-me

Papers

Boosting Co-teaching with Compression Regularization for Label Noise

2021-04-28 · Yingyi Chen, Xi Shen, Shell Xu Hu, Johan A. K. Suykens

In this paper, we study the problem of learning image classification models in the presence of label noise. We revisit a simple compression regularization named Nested Dropout. We find that Nested Dropout, though originally proposed to perform fast information retrieval and adaptive data compression, can properly regularize a neural network to combat label noise. Moreover, owing to its simplicity, it can be easily combined with Co-teaching to further boost the performance. Our final model remains simple yet effective: it achieves comparable or even better performance than the state-of-the-art approaches on two real-world datasets with label noise which are Clothing1M and ANIMAL-10N. On Clothing1M, our approach obtains 74.9% accuracy which is slightly better than that of DivideMix. On ANIMAL-10N, we achieve 84.1% accuracy while the best public result by PLC is 83.4%. We hope that our simple approach can be served as a strong baseline for learning with label noise. Our implementation is available at https://github.com/yingyichen-cyy/Nested-Co-teaching.

📄 PDF Abstract BibTeX arXiv:2104.13766

Code (1)

yingyichen-cyy/Nested-Co-teaching pytorch

Tasks

Data Compressionimage-classificationImage ClassificationLearning with noisy labelsRetrieval

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Compressing Features for Learning with Noisy Labels

2022-06-27 · Yingyi Chen, Shell Xu Hu, Xi Shen, Chunrong Ai 외

Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be releva…

Feature CompressionFeature ImportanceImage ClassificationInductive Bias+1

A Labelled Sample Compression Scheme of Size at Most Quadratic in the VC Dimension

2022-12-24 · Farnam Mansouri, Sandra Zilles

This paper presents a construction of a proper and stable labelled sample compression scheme of size $O(\VCD^2)$ for any finite concept class, where $\VCD$ denotes the Vapnik-Chervonenkis Dimension. The construction is b…

Open-Ended Question Answering

Agreement or Disagreement in Noise-tolerant Mutual Learning?

2022-03-29 · Jiarun Liu, Daguang Jiang, Yukun Yang, Ruirui Li

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label b…

Fighting over-fitting with quantization for learning deep neural networks on noisy labels

2023-03-21 · Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny, Kevin Bailly

The rising performance of deep neural networks is often empirically attributed to an increase in the available computational power, which allows complex models to be trained upon large amounts of annotated data. However,…

Action Unit DetectionFacial Action Unit DetectionQuantization

Boosting in the presence of label noise

2013-09-26 · Jakramate Bootkrajang, Ata Kaban

Boosting is known to be sensitive to label noise. We studied two approaches to improve AdaBoost's robustness against labelling errors. One is to employ a label-noise robust classifier as a base learner, while the other i…