Polarized self-attention: Towards high-quality pixel-wise mapping
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 …
computer vision tasks, such as estimating keypoint heatmaps and segmentation masks …
Boundary-aware feature propagation for scene segmentation
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 …
feature similarity of the same object while keeping the feature discrimination of different …
Learning statistical texture for semantic segmentation
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 …
high-level semantic features with CNNs. In order to maintain a precise boundary, low-level …
Attention gate resU-Net for automatic MRI brain tumor segmentation
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 …
treatment of MRI brain tumors. It helps doctors to locate and measure tumors, as well as …
Multiscale deep equilibrium models
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 …
(MDEQ), suited to large-scale and highly hierarchical pattern recognition domains. An …
K-net: Towards unified image segmentation
Semantic, instance, and panoptic segmentations have been addressed using different and
specialized frameworks despite their underlying connections. This paper presents a unified …
specialized frameworks despite their underlying connections. This paper presents a unified …
A survey on deep learning-based architectures for semantic segmentation on 2d images
I Ulku, E Akagündüz - Applied Artificial Intelligence, 2022 - Taylor & Francis
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 …
ability of convolutional neural networks (CNN) in creating semantic, high-level and …
DecoupleNet: Decoupled network for domain adaptive semantic segmentation
Unsupervised domain adaptation in semantic segmentation alleviates the reliance on
expensive pixel-wise annotation. It uses a labeled source domain dataset as well as …
expensive pixel-wise annotation. It uses a labeled source domain dataset as well as …
Learning delicate local representations for multi-person pose estimation
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 …
aggregates features with the same spatial size (Intra-level features) efficiently to obtain …
Learning position and target consistency for memory-based video object segmentation
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 …
Multiple works have shown that memory-based approaches can be effective for video object …