PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance

ArXi:2605.27128v1 Announce Type: cross Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real world environments often requires the ability to on the entire dataset. This capability is known as continual learning. In this regard, the standard fine-tuning methods in deep learning often fail due to catastrophic forgetting, where the model learns new information but forgets previously trained and learned classes.