paper-with-me

Papers

Instance-Dependent Noisy Label Learning via Graphical Modelling

2022-09-02 · Arpit Garg, Cuong Nguyen, Rafael Felix, Thanh-Toan Do, Gustavo Carneiro

Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymmetric and instance-dependent noise (IDN), with IDN being the only type that depends on image information. Such dependence on image information makes IDN a critical type of label noise to study, given that labelling mistakes are caused in large part by insufficient or ambiguous information about the visual classes present in images. Aiming to provide an effective technique to address IDN, we present a new graphical modelling approach called InstanceGM, that combines discriminative and generative models. The main contributions of InstanceGM are: i) the use of the continuous Bernoulli distribution to train the generative model, offering significant training advantages, and ii) the exploration of a state-of-the-art noisy-label discriminative classifier to generate clean labels from instance-dependent noisy-label samples. InstanceGM is competitive with current noisy-label learning approaches, particularly in IDN benchmarks using synthetic and real-world datasets, where our method shows better accuracy than the competitors in most experiments.

📄 PDF Abstract BibTeX arXiv:2209.00906

Code (1)

arpit2412/InstanceGM pytorch

Tasks

Image ClassificationLearning with noisy labels

Similar Papers 제목 키워드 기반

Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation

2023-05-31 · Arpit Garg, Cuong Nguyen, Rafael Felix, Thanh-Toan Do 외

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a …

Mixed Blessing: Class-Wise Embedding guided Instance-Dependent Partial Label Learning

2024-12-06 · Fuchao Yang, Jianhong Cheng, Hui Liu, Yongqiang Dong 외

In partial label learning (PLL), every sample is associated with a candidate label set comprising the ground-truth label and several noisy labels. The conventional PLL assumes the noisy labels are randomly generated (ins…

Partial Label Learning

Rethinking the Value of Labels for Instance-Dependent Label Noise Learning

2023-05-10 · Hanwen Deng, Weijia Zhang, Min-Ling Zhang

Label noise widely exists in large-scale datasets and significantly degenerates the performances of deep learning algorithms. Due to the non-identifiability of the instance-dependent noise transition matrix, most existin…

Representation Learning

Instance-dependent Label Distribution Estimation for Learning with Label Noise

2022-12-16 · Zehui Liao, Shishuai Hu, Yutong Xie, Yong Xia

Noise transition matrix (NTM) estimation is a promising approach for learning with label noise. It can infer clean posterior probabilities, known as Label Distribution (LD), based on noisy ones and reduce the impact of n…

image-classificationImage Classification

An Instance-Dependent Simulation Framework for Learning with Label Noise

2021-07-23 · Keren Gu, Xander Masotto, Vandana Bachani, Balaji Lakshminarayanan 외

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human…

Learning with noisy labels