Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
This addresses the challenge of developing interpretable and efficient segmentation models for realistic, data-scarce continual learning scenarios, though it appears incremental as it builds on existing CSS and IL frameworks.
The paper tackles the problem of continual semantic segmentation with limited data by proposing Learning at a Glance (LAG), which uses semantic-invariance modelling to balance knowledge preservation and new learning, achieving competitive efficiency and superior performance under data-limited conditions.
Continual semantic segmentation (CSS) based on incremental learning (IL) is a great endeavour in developing human-like segmentation models. However, current CSS approaches encounter challenges in the trade-off between preserving old knowledge and learning new ones, where they still need large-scale annotated data for incremental training and lack interpretability. In this paper, we present Learning at a Glance (LAG), an efficient, robust, human-like and interpretable approach for CSS. Specifically, LAG is a simple and model-agnostic architecture, yet it achieves competitive CSS efficiency with limited incremental data. Inspired by human-like recognition patterns, we propose a semantic-invariance modelling approach via semantic features decoupling that simultaneously reconciles solid knowledge inheritance and new-term learning. Concretely, the proposed decoupling manner includes two ways, i.e., channel-wise decoupling and spatial-level neuron-relevant semantic consistency. Our approach preserves semantic-invariant knowledge as solid prototypes to alleviate catastrophic forgetting, while also constraining sample-specific contents through an asymmetric contrastive learning method to enhance model robustness during IL steps. Experimental results in multiple datasets validate the effectiveness of the proposed method. Furthermore, we introduce a novel CSS protocol that better reflects realistic data-limited CSS settings, and LAG achieves superior performance under multiple data-limited conditions.