Modeling the Background for Incremental Learning in Semantic Segmentation
This work solves the problem of incremental learning in semantic segmentation for computer vision applications, offering a novel approach to handle background class shifts, though it is incremental in nature.
The paper tackles catastrophic forgetting in incremental learning for semantic segmentation by addressing the semantic distribution shift of background pixels, resulting in significant performance improvements over state-of-the-art methods on Pascal-VOC 2012 and ADE20K datasets.
Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their model as new classes are available but the original training set is not retained. This paper addresses this problem in the context of semantic segmentation. Current strategies fail on this task because they do not consider a peculiar aspect of semantic segmentation: since each training step provides annotation only for a subset of all possible classes, pixels of the background class (i.e. pixels that do not belong to any other classes) exhibit a semantic distribution shift. In this work we revisit classical incremental learning methods, proposing a new distillation-based framework which explicitly accounts for this shift. Furthermore, we introduce a novel strategy to initialize classifier's parameters, thus preventing biased predictions toward the background class. We demonstrate the effectiveness of our approach with an extensive evaluation on the Pascal-VOC 2012 and ADE20K datasets, significantly outperforming state of the art incremental learning methods.