High resolution and advanced semantic representation are both vital for dense prediction.
Empirically, low-resolution feature maps often achieve stronger semantic representation …

Tasks that involve high-resolution dense prediction require a modeling of both local and
global patterns in a large input field. Although the local and global structures often depend …

High-resolution dense prediction enables many appealing real-world applications, such as
computational photography, autonomous driving, etc. However, the vast computational cost …

Recent advancements in deep neural networks have made remarkable leap-forwards in
dense image prediction. However, the issue of feature alignment remains as neglected by …

As deep neural networks become the state-of-the-art approach in the field of computer vision
for dense prediction tasks, many methods have been developed for automatic estimation of …

Although fully convolution networks (FCNs) have dominated dense prediction tasks (eg,
semantic segmentation, depth estimation and object detection) for decades, they are …

Dense prediction tasks, such as semantic segmentation, depth estimation, and surface
normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or …

The pixel-wise dense prediction tasks based on weakly supervisions currently use Class
Attention Maps (CAM) to generate pseudo masks as ground-truth. However, the existing …

Previous multi-task dense prediction studies developed complex pipelines such as multi-
modal distillations in multiple stages or searching for task relational contexts for each task …

High-resolution dense prediction enables many appealing real-world applications, such as
computational photography, autonomous driving, etc. However, the vast computational cost …