Rank3 Code for ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection, Task 3
Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention - Accepted in CVPR 2025
ISIC 2018 - Skin Lesion Classification for Melanoma Detection
Skin lesion segmentation with a U-Net, using the dataset from ISIC challenge 2018.
Skin lesion classification for the ISIC2018 challenge attempted at Persitent Systems
ISIC Challenge 2018 - Task 3 - PyTorch
CNN ensemble for skin lesion classification — BACC 0.846 ± 0.009 · Clinical threshold calibration · ResNet-50 + DenseNet-121 + EfficientNet-B3 · ISIC 2018 Task 3
ISIC 2018 dermoscopy deep learning — all three tasks, a concept-bottleneck experiment, a skin-tone fairness audit, and a scored entry on the live ISIC MILK10k leaderboard (macro F1 0.422). My first DL project, retrained in 2026 with an honest retrospective.
Controlled PyTorch experiments for skin lesion segmentation on ISIC 2018 using U-Net, BCE + Dice loss, augmentation, and Attention U-Net.
To associate your repository with the isic2018 topic, visit your repo's landing page and select "manage topics."