We address the pixel-wise mapping problem that commonly exists in the fine-grained
computer vision tasks, such as estimating keypoint heatmaps and segmentation masks …

In this work, we address the challenging issue of scene segmentation. To increase the
feature similarity of the same object while keeping the feature discrimination of different …

Existing semantic segmentation works mainly focus on learning the contextual information in
high-level semantic features with CNNs. In order to maintain a precise boundary, low-level …

Brain tumor segmentation technology plays a pivotal role in the process of diagnosis and
treatment of MRI brain tumors. It helps doctors to locate and measure tumors, as well as …

We propose a new class of implicit networks, the multiscale deep equilibrium model
(MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An …

Semantic, instance, and panoptic segmentations have been addressed using different and
specialized frameworks despite their underlying connections. This paper presents a unified …

Semantic segmentation is the pixel-wise labeling of an image. Boosted by the extraordinary
ability of convolutional neural networks (CNN) in creating semantic, high-level and …

Unsupervised domain adaptation in semantic segmentation alleviates the reliance on
expensive pixel-wise annotation. It uses a labeled source domain dataset as well as …

In this paper, we propose a novel method called Residual Steps Network (RSN). RSN
aggregates features with the same spatial size (Intra-level features) efficiently to obtain …

This paper studies the problem of semi-supervised video object segmentation (VOS).
Multiple works have shown that memory-based approaches can be effective for video object …