| Téléchargement | - Voir la version de l’auteur : Transferring knowledge for food image segmentation using transformers and convolutions (PDF, 2.5 Mio)
|
|---|
| DOI | Trouver le DOI : https://doi.org/10.48550/arXiv.2306.09203 |
|---|
| Auteur | Rechercher : Sinha, Grant; Rechercher : Parmar, Krish; Rechercher : Azimi, Hilda1; Rechercher : Tai, Amy; Rechercher : Chen, Yuhao; Rechercher : Wong, Alexander; Rechercher : Xi, Pengcheng1Identifiant ORCID : https://orcid.org/0000-0003-3236-5234 |
|---|
| Affiliation | - Conseil national de recherches du Canada. Technologies numériques
|
|---|
| Format | Texte, Préimpression |
|---|
| Conférence | The 2nd Workshop on Computer Vision in the Wild, June 19, 2023, Vancouver, British Columbia, Canada |
|---|
| Résumé | Food image segmentation is an important task that has ubiquitous applications, such as estimating the nutritional value of a plate of food. Although machine learning models have been used for segmentation in this domain, food images pose several challenges. One challenge is that food items can overlap and mix, making them difficult to distinguish. Another challenge is the degree of inter-class similarity and intra-class variability, which is caused by the varying preparation methods and dishes a food item may be served in. Additionally, class imbalance is an inevitable issue in food datasets. To address these issues, two models are trained and compared, one based on convolutional neural networks and the other on Bidirectional Encoder representation for Image Transformers (BEiT). The models are trained and valuated using the FoodSeg103 dataset, which is identified as a robust benchmark for food image segmentation. The BEiT model outperforms the previous state-of the-art model by achieving a mean intersection over union of 49.4 on FoodSeg103. This study provides insights into transfering knowledge using convolution and Transformer based approaches in the food image domain. |
|---|
| Date de publication | 2023-06-19 |
|---|
| Maison d’édition | Cornell University |
|---|
| Licence | |
|---|
| Dans | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Non |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | a44c3198-ab99-4640-885c-f881841f369c |
|---|
| Enregistrement créé | 2023-11-03 |
|---|
| Enregistrement modifié | 2023-11-08 |
|---|
