Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentation
This work addresses the problem of data scarcity in semantic segmentation for AI/computer vision researchers, offering an incremental improvement by integrating new modules into existing frameworks.
The paper tackles the challenge of model generalization in few-shot semantic segmentation due to distribution shift between base and novel classes, proposing a class-shared memory module and an uncertainty-based feature augmentation module that achieve superior performance over state-of-the-art methods on PASCAL-5^i and COCO-20^i datasets.
The performance of supervised semantic segmentation methods highly relies on the availability of large-scale training data. To alleviate this dependence, few-shot semantic segmentation (FSS) is introduced to leverage the model trained on base classes with sufficient data into the segmentation of novel classes with few data. FSS methods face the challenge of model generalization on novel classes due to the distribution shift between base and novel classes. To overcome this issue, we propose a class-shared memory (CSM) module consisting of a set of learnable memory vectors. These memory vectors learn elemental object patterns from base classes during training whilst re-encoding query features during both training and inference, thereby improving the distribution alignment between base and novel classes. Furthermore, to cope with the performance degradation resulting from the intra-class variance across images, we introduce an uncertainty-based feature augmentation (UFA) module to produce diverse query features during training for improving the model's robustness. We integrate CSM and UFA into representative FSS works, with experimental results on the widely-used PASCAL-5$^i$ and COCO-20$^i$ datasets demonstrating the superior performance of ours over state of the art.