Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation
This work addresses the challenge of improving segmentation accuracy in weakly supervised settings, which is incremental as it builds on existing methods by enhancing data augmentation.
The paper tackles the problem of weakly supervised semantic segmentation by addressing the issue of models relying on co-occurring context rather than object features, and introduces a Context Decoupling Augmentation method that achieves new state-of-the-art results on the PASCAL VOC 2012 dataset.
Data augmentation is vital for deep learning neural networks. By providing massive training samples, it helps to improve the generalization ability of the model. Weakly supervised semantic segmentation (WSSS) is a challenging problem that has been deeply studied in recent years, conventional data augmentation approaches for WSSS usually employ geometrical transformations, random cropping and color jittering. However, merely increasing the same contextual semantic data does not bring much gain to the networks to distinguish the objects, e.g., the correct image-level classification of "aeroplane" may be not only due to the recognition of the object itself, but also its co-occurrence context like "sky", which will cause the model to focus less on the object features. To this end, we present a Context Decoupling Augmentation (CDA) method, to change the inherent context in which the objects appear and thus drive the network to remove the dependence between object instances and contextual information. To validate the effectiveness of the proposed method, extensive experiments on PASCAL VOC 2012 dataset with several alternative network architectures demonstrate that CDA can boost various popular WSSS methods to the new state-of-the-art by a large margin.