Our article proposes an end-to-end method for FSSS in modern artificial intelligence by addressing the challenging task of accurately segmenting new classes with limited annotated samples. Our method achieves state-of-the-art performance on several benchmark datasets compared to existing methods. Specifically, our proposed method has demonstrated superior performance in segmenting previously unseen objects using only a small number of annotated samples, which has tremendous implications for a wide range of real-world applications, such as medical image analysis, autonomous driving, and robotics. The impact of our research lies not only in its theoretical contributions but also in its potential practical applications that can revolutionize the way we method complex visual tasks with limited labeled data. Our work contributes to the advancement of few-shot learning and provides a valuable tool for improving the efficiency and accuracy of semantic segmentation in various domains.

Few-shot semantic segmentation (FSSS) is a pivotal and prevalent research task for advancing the field of artificial intelligence. The task entails learning to differentiate between various classes in a support set and leveraging this knowledge on samples within a query set. However, traditional deep learning methods tend to underperform in this context due to limited training samples and subtle correlations between query and support images that are inadequately utilized. Existing methods for FSSS often compress support information into prototype categories or utilize only partial pixel-level support information, resulting in a significant impact. In this article, we propose a novel auto FSSS method that employs dense multicross self-attention and adaptive gate perception units to tackle this challenge. Specifically, our proposed method treats each query pixel as a label and predicts its segmentation label as the sum of labels of all support pixels. The method fully utilizes foreground...