From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model

2022-05-02 · HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon

Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing methods on noisy label have focused on modifying the classifier during the training procedure. It has two potential problems. First, these methods are not applicable to a pre-trained classifier without further access to training. Second, it is not easy to train a classifier and regularize all negative effects from noisy labels, simultaneously. We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels. Through the introduction and estimation of a new type of transition matrix via generative model, NPC corrects the noisy prediction from the pre-trained classifier to the true label as a post-processing scheme. We prove that NPC theoretically aligns with the transition matrix based methods. Yet, NPC empirically provides more accurate pathway to estimate true label, even without involvement in classifier learning. Also, NPC is applicable to any classifier trained with noisy label methods, if training instances and its predictions are available. Our method, NPC, boosts the classification performances of all baseline models on both synthetic and real-world datasets. The implemented code is available at https://github.com/BaeHeeSun/NPC.

📄 PDF Abstract BibTeX arXiv:2205.00690

Code (2)

BaeHeeSun/NPC 공식 구현 pytorch

debajyotid2/noisy_prediction_calibration tf

Tasks

Learning with noisy labels Prediction

DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modeling

2023-05-30 · Yuchen Zhuang, Yue Yu, Lingkai Kong, Xiang Chen 외

Learning from noisy labels is a challenge that arises in many real-world applications where training data can contain incorrect or corrupted labels. When fine-tuning language models with noisy labels, models can easily o…

Denoising

Error-Bounded Correction of Noisy Labels

2020-11-19 · ICML 2020 1 · Songzhu Zheng, Pengxiang Wu, Aman Goswami, Mayank Goswami 외

To collect large scale annotated data, it is inevitable to introduce label noise, i.e., incorrect class labels. To be robust against label noise, many successful methods rely on the noisy classifiers (i.e., models traine…

Image Classification

Estimating the Conformal Prediction Threshold from Noisy Labels

2025-01-22 · Coby Penso, Jacob Goldberger, Ethan Fetaya

Conformal Prediction (CP) is a method to control prediction uncertainty by producing a small prediction set, ensuring a predetermined probability that the true class lies within this set. This is commonly done by definin…

Conformal Prediction image-classification Image Classification Medical Image Classification+1

Iterative Learning with Open-set Noisy Labels

2018-03-31 · CVPR 2018 6 · Yisen Wang, Weiyang Liu, Xingjun Ma, James Bailey 외

Large-scale datasets possessing clean label annotations are crucial for training Convolutional Neural Networks (CNNs). However, labeling large-scale data can be very costly and error-prone, and even high-quality datasets…

Twin Contrastive Learning with Noisy Labels

2023-03-13 · CVPR 2023 1 · Zhizhong Huang, Junping Zhang, Hongming Shan

Learning from noisy data is a challenging task that significantly degenerates the model performance. In this paper, we present TCL, a novel twin contrastive learning model to learn robust representations and handle noisy…

Contrastive Learning Image Classification Learning with noisy labels