Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection
This work addresses the challenge of detecting and segmenting artefacts in endoscopic images, which is crucial for improving medical diagnostics, but it is incremental as it builds on existing ensemble methods.
The paper tackled the problem of endoscopic artefact segmentation and detection by proposing a multi-plateau ensemble of FPN with EfficientNet for segmentation and a three-model ensemble of RetinaNet and FasterRCNN for detection, achieving competitive results in the Endoscopic Artefact Detection Challenge.
Endoscopic artefact detection challenge consists of 1) Artefact detection, 2) Semantic segmentation, and 3) Out-of-sample generalisation. For Semantic segmentation task, we propose a multi-plateau ensemble of FPN (Feature Pyramid Network) with EfficientNet as feature extractor/encoder. For Object detection task, we used a three model ensemble of RetinaNet with Resnet50 Backbone and FasterRCNN (FPN + DC5) with Resnext101 Backbone}. A PyTorch implementation to our approach to the problem is available at https://github.com/ubamba98/EAD2020.