Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/139216
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Instance-Dependent Noisy Label Learning via Graphical Modelling |
Author: | Garg, A. Nguyen, C. Felix, R. Do, T.-T. Carneiro, G. |
Citation: | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), 2023, pp.2287-2297 |
Publisher: | IEEE |
Publisher Place: | Online |
Issue Date: | 2023 |
Series/Report no.: | IEEE Winter Conference on Applications of Computer Vision |
ISBN: | 9781665493475 |
ISSN: | 2472-6737 2642-9381 |
Conference Name: | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2 Jan 2023 - 7 Jan 2023 : Waikoloa, HI, USA) |
Statement of Responsibility: | Arpit Garg, Cuong Nguyen, Rafael Felix, Thanh-Toan Do, and Gustavo Carneiro |
Abstract: | 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 instancedependent 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 experiments¹. |
Rights: | ©2023 IEEE |
DOI: | 10.1109/wacv56688.2023.00232 |
Grant ID: | http://purl.org/au-research/grants/arc/DP180103232 http://purl.org/au-research/grants/arc/FT190100525 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/10030081/proceeding |
Appears in Collections: | Australian Institute for Machine Learning publications Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.