Mask-Guided Attention and Episode Adaptive Weights for Few-Shot Segmentation

Few-shot segmentation aims to segment objects with novel classes in a query image, given a support set which consists of few annotated support images. A key factor in few-shot segmentation is to effectively exploit information for the target classes from the support set. In addition, we argue that the overall quality of information available in each training episode varies depending on the given support samples. In this paper, we propose Mask-Guided Attention module to extract more beneficial features for few-shot segmentation from the support images. Taking advantage of the support masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. Furthermore, we propose Episode Adaptive Weight to balance the training between different episodes. It adaptively adjusts loss weight according to the difficulty of each episode determined by self-supervised segmentation loss of support images and encourages the model to pay more attention to more difficult episodes. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.