Label Sharing Incremental Learning Framework for Independent Multi-Label Segmentation Tasks
This work addresses the challenge of parameter and data efficiency in multi-dataset segmentation for medical imaging, though it is incremental as it builds on existing multi-task and shared encoder concepts.
The paper tackles the problem of building segmentation models for multiple datasets with different label sets by proposing a label sharing framework that maps individual labels to a common space, enabling a single model to handle all tasks. The method is validated on medical image segmentation datasets, showing improvements in performance and incremental learning ability compared to alternative approaches.
In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures with shared encoders and multiple segmentation heads or shared weights with compound labels can also be made use of. This work proposes a novel label sharing framework where a shared common label space is constructed and each of the individual label sets are systematically mapped to the common labels. This transforms multiple datasets with disparate label sets into a single large dataset with shared labels, and therefore all the segmentation tasks can be addressed by learning a single model. This eliminates the need for task specific adaptations in network architectures and also results in parameter and data efficient models. Furthermore, label sharing framework is naturally amenable for incremental learning where segmentations for new datasets can be easily learnt. We experimentally validate our method on various medical image segmentation datasets, each involving multi-label segmentation. Furthermore, we demonstrate the efficacy of the proposed method in terms of performance and incremental learning ability vis-a-vis alternative methods.