- Title
- Melanoma classification using efficientnets and ensemble of models with different input resolution
- Creator
- Karki, Sagar; Kulkarni, Pradnya; Stranieri, Andrew
- Date
- 2021
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/186141
- Identifier
- vital:16817
- Identifier
-
https://doi.org/10.1145/3437378.3437396
- Identifier
- ISBN:9781450389563 (ISBN)
- Abstract
- Early and accurate detection of melanoma with data analytics can make treatment more effective. This paper proposes a method to classify melanoma cases using deep learning on dermoscopic images. The method demonstrates that heavy augmentation during training and testing produces promising results and warrants further research. The proposed method has been evaluated on the SIIM-ISIC Melanoma Classification 2020 dataset and the best ensemble model achieved 0.9411 area under the ROC curve on hold out test data. © 2021 ACM.
- Publisher
- Association for Computing Machinery
- Relation
- 2021 Australasian Computer Science Week Multiconference, ACSW 2021, Virtual, Online, 1-5 February 2021, ACM International Conference Proceeding Series
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright AMC© 2021 Association for Computing Machinery
- Rights
- Open Access
- Subject
- CNN; Deep learning; EfficientNet; Kaggle; Melanoma; Skin lesion classification
- Full Text
- Reviewed
- Hits: 636
- Visitors: 583
- Downloads: 102
| Thumbnail | File | Description | Size | Format | |||
|---|---|---|---|---|---|---|---|
| View Details Download | SOURCE2 | Accepted version | 738 KB | Adobe Acrobat PDF | View Details Download |