DUAL-ATTENTION NETWORK FOR FEW-SHOT SEGMENTATION

Few-shot segmentation aims at segmenting target object areas with only a few labeled samples. Previous methods extract class-specific prototypes to guide segmentation. However, using one or more prototypes to represent the whole object inevitably drops vital spatial information, ignoring many details in original images. To address the issue, we propose a Dual-Attention Network (DANet) for few-shot segmentation. Firstly, a light-dense attention module is proposed to set up pixel-wise relations between feature pairs at different levels to activate object regions, which can leverage semantic information in a coarse-to-fine manner. Secondly, in contrast to the previous prototype-based methods that offer a holistic representation for each object class, we propose a prototypical channel attention module which incorporates channel interdependencies to enhance the discriminative capacity of features. The extensive experiments on two benchmarks show that our approach outperforms the state-of-the-arts in most cases.