Food Recognition in the Presence of Label Noise

Papathanail, Ioannis; Lu, Ya; Ghosh, Arindam; Mougiakakou, Stavroula (21 February 2021). Food Recognition in the Presence of Label Noise. In: Del Bimbo, Alberto; Cucchiara, Rita; Sclaroff, Stan; Farinella, Giovanni Maria; Mei, Tao; Bertini, Marco; Escalante, Hugo Jair; Vezzani, Roberto (eds.) Pattern Recognition. ICPR International Workshops and Challenges. Lecture Notes in Computer Science: Vol. 12665 (pp. 617-628). Springer, Cham 10.1007/978-3-030-68821-9_49

[img] Text
Papathanail2021_Chapter_FoodRecognitionInThePresenceOf.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (2MB)
[img]
Preview
Text
Food_Recognition_in_the_Presence_of_Label_Noise.pdf - Accepted Version
Available under License Publisher holds Copyright.

Download (500kB) | Preview

The objective of multi-label image classification is to recognise several objects that appear within a single image. In the current paper, we consider the task of multi-label food recognition, where the images contain foods for which the labels in the training set are noisy, as they are annotated by inexperienced annotators. We now propose that a noise adaptation layer should be appended to a pretrained baseline model, in order to make it possible to learn from these noisy labels. From the baseline model, predictions are made on the training set and a confusion matrix is created from these predictions and the noisy labels. This confusion matrix is used to initialise the weights of the noise layer and the full model is retrained on the training set. The final predictions for the testing set are made from the baseline model, after its weights have been readjusted by the noise layer. We show that the final model significantly improves performance on noisy datasets.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research > ARTORG Center - AI in Health and Nutrition

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Papathanail, Ioannis, Lu, Ya, Mougiakakou, Stavroula

Subjects:

600 Technology
600 Technology > 610 Medicine & health
600 Technology > 620 Engineering

ISSN:

1611-3349

ISBN:

978-3-030-68821-9

Series:

Lecture Notes in Computer Science

Publisher:

Springer, Cham

Funders:

[UNSPECIFIED] Innosuisse

Language:

English

Submitter:

Stavroula Mougiakakou

Date Deposited:

28 May 2021 17:00

Last Modified:

05 Dec 2022 15:48

Publisher DOI:

10.1007/978-3-030-68821-9_49

BORIS DOI:

10.7892/boris.152855

URI:

https://boris.unibe.ch/id/eprint/152855

Actions (login required)

Edit item Edit item
Provide Feedback