Visual semantic segmentation aims at separating a visual sample into diverse blocks with
specific semantic attributes and identifying the category for each block, and it plays a crucial …

Despite the remarkable performance of deep learning methods on various tasks, most
cutting-edge models rely heavily on large-scale annotated training examples, which are …

Existing few-shot segmentation methods have achieved great progress based on the
support-query matching framework. But they still heavily suffer from the limited coverage of …

Few-shot semantic segmentation aims at learning to segment a target object from a query
image using only a few annotated support images of the target class. This challenging task …

Few-shot segmentation has been attracting a lot of attention due to its effectiveness to
segment unseen object classes with a few annotated samples. Most existing approaches …

Few-shot semantic segmentation (FSS) has great potential for medical imaging applications.
Most of the existing FSS techniques require abundant annotated semantic classes for …

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then
introduced into the optimization community. BLO is able to handle problems with a …

Fully-supervised deep learning segmentation models are inflexible when encountering new
unseen semantic classes and their fine-tuning often requires significant amounts of …

Compared to traditional machine learning, deep learning can learn deeper abstract data
representation and understand scattered data properties. It has gained considerable …

Abstract Few-shot segmentation~(FSS) aims at performing semantic segmentation on novel
classes given a few annotated support samples. With a rethink of recent advances, we find …