Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Image segmentation is a branch of digital image processing which has numerous
applications in the field of analysis of images, augmented reality, machine vision, and many …

Very recently, a variety of vision transformer architectures for dense prediction tasks have
been proposed and they show that the design of spatial attention is critical to their success in …

Image restoration tasks demand a complex balance between spatial details and high-level
contextualized information while recovering images. In this paper, we propose a novel …

In the Internet-of-Things (IoT) era, billions of sensors and devices collect and process data
from the environment, transmit them to cloud centers, and receive feedback via the Internet …

Feature fusion, the combination of features from different layers or branches, is an
omnipresent part of modern network architectures. It is often implemented via simple …

Encoder-decoder networks are state-of-the-art approaches to biomedical image
segmentation, but have two problems: ie, the widely used pooling operations may discard …

Camouflaged object segmentation (COS) aims to identify objects that are" perfectly"
assimilate into their surroundings, which has a wide range of valuable applications. The key …

State-of-the-art semantic segmentation methods require sufficient labeled data to achieve
good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation …

Low-level details and high-level semantics are both essential to the semantic segmentation
task. However, to speed up the model inference, current approaches almost always sacrifice …