The loss function, also known as cost function, is used for training a neural network or other
machine learning models. Over the past decade, researchers have designed many loss …

Recent advances in deep learning have shown excellent performance in various scene
understanding tasks. However, in some complex environments or under challenging …

Existing leading methods for spectral reconstruction (SR) focus on designing deeper or
wider convolutional neural networks (CNNs) to learn the end-to-end map** from the RGB …

Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with
an encoder-decoder architecture. The encoder progressively reduces the spatial resolution …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Spatial pooling has been proven highly effective to capture long-range contextual
information for pixel-wise prediction tasks, such as scene parsing. In this paper, beyond …

In this paper, we study the context aggregation problem in semantic segmentation.
Motivated by that the label of a pixel is the category of the object that the pixel belongs to, we …

Transformer, first applied to the field of natural language processing, is a type of deep neural
network mainly based on the self-attention mechanism. Thanks to its strong representation …

Many learning-based algorithms have been developed to solve the inverse problem of
coded aperture snapshot spectral imaging (CASSI). However, CNN-based methods show …

Depth information has proven to be a useful cue in the semantic segmentation of RGB-D
images for providing a geometric counterpart to the RGB representation. Most existing works …