Searching for Contextual Subtasks for Semantic Segmentation Public
Downloadable Contentopen in viewer
Deep learning approaches for semantic segmentation have achieved tremendous success through their ability to model long-range scene context. However, by training for per-pixel classification, these methods fail to address the issue of class imbalance in segmentation datasets. Our work approaches segmentation from a contextual modeling standpoint by introducing novel subtasks as a human-provided hint or an auxiliary training signal. We first validate candidate subtasks through human-in-the-loop techniques to correct mistakes in segmentation, improving the mIoU of UPerNet-ResNet50 from 42.05 to 48.70 without any trained parameters. We then demonstrate the potential for multi-task learning of these subtasks with segmentation through a study of task gradients and end-to-end training.
- Defense date
- Date created
- Resource type
- Rights statement
Permanent link to this page: https://digital.wpi.edu/show/fb494c84s