Hardware
Deep Feature Pyramid Convolutional Networks with In-Place Activated Batch Normalization for Automated Skin Lesion Boundary Segmentation
arXiv:1812.00877v2 Announce Type: replace Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant melanoma,
arXiv:1812.00877v2 Announce Type: replace Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant melanoma, but remains challenging due to fuzzy margins, occluding artifacts such as hair and blood vessels, low contrast, and high inter-patient variability. This work presents a memory-efficient deep convolutional neural network framework for lesion boundary segmentation, developed for the ISIC 2018 Challenge (Task 1: Lesion Boundary Segmentation). A U-Net-style encoder-decoder architecture is adapted using Wide ResNet38 and Dual Path Network (DPN) backbones with a Feature Pyramid Network (FPN) decoder, pretrained on ImageNet. In-Place Activated Batch Normalization (InPlace-ABN) reduces memory consumption during training, allowing higher-capacity ensembling under standard GPU memory constraints, combined with five-fold cross-validation, extensive augmentation, snapshot ensembling, and test-time augmentation. The best-performing model achieves a Thresholded Jaccard score of 0.752 on the ISIC 2018 Challenge evaluation, with single-model configurations scoring between 0.700 and 0.750; InPlace-ABN reduces memory consumption by approximately 25%. To contextualize this result against current practice, a simplified single-model U-Net baseline retrained in 2026 using standard modern tooling is also reported, achieving a Dice score of 0.8443 (IoU 0.7608, Thresholded Jaccard 0.6680), which highlights the substantial contribution of ensembling and pretraining to the original result. This work does not claim state-of-the-art segmentation accuracy; rather, it documents a memory-efficient training approach that enables higher-capacity ensembling under constrained GPU resources, a practical consideration for training high-capacity segmentation models in settings with limited computational budgets.
Related
- BATS: Resource-Efficient Volumetric Segmentation with Boundary-Aware Mixed-Resolution Tokens
- Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
- MVSegNet: A Lightweight Boundary-Aware Network for Fetal Lateral Ventricle Segmentation and Atrial Width Estimation in Prenatal Ultrasound
Source: arXiv cs.CV | 2026-08-26