Related papers: Scale Equivariant U-Net
This study explores the potential of graph neural networks (GNNs) to enhance semantic segmentation across diverse image modalities. We evaluate the effectiveness of a novel GNN-based U-Net architecture on three distinct datasets: PascalVOC,…
Medical image segmentation is a critical task in computer vision, with UNet serving as a milestone architecture. The typical component of UNet family is the skip connection, however, their skip connections face two significant limitations:…
State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…
ReduNet is a deep neural network model that leverages the principle of maximal coding rate \textbf{redu}ction to transform original data samples into a low-dimensional, linear discriminative feature representation. Unlike traditional deep…
Semi-supervised learning is increasingly popular in medical image segmentation due to its ability to leverage large amounts of unlabeled data to extract additional information. However, most existing semi-supervised segmentation methods…
Unsupervised domain adaptation aims to learn a model of classifier for unlabeled samples on the target domain, given training data of labeled samples on the source domain. Impressive progress is made recently by learning invariant features…
U-Net is a widely adopted neural network in the domain of medical image segmentation. Despite its quick embracement by the medical imaging community, its performance suffers on complicated datasets. The problem can be ascribed to its simple…
Slimmable networks are a family of neural networks that can instantly adjust the runtime width. The width can be chosen from a predefined widths set to adaptively optimize accuracy-efficiency trade-offs at runtime. In this work, we propose…
Semantic segmentation with dense pixel-wise annotation has achieved excellent performance thanks to deep learning. However, the generalization of semantic segmentation in the wild remains challenging. In this paper, we address the problem…
How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the…
Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key…
Extending the translation equivariance property of convolutional neural networks to larger symmetry groups has been shown to reduce sample complexity and enable more discriminative feature learning. Further, exploiting additional symmetries…
U-Net has been widely used for segmenting abdominal organs, achieving promising performance. However, when it is used for multi-organ segmentation, first, it may be limited in exploiting global long-range contextual information due to the…
This work proposes a novel framework, Uncertainty-Guided Cross Attention Ensemble Mean Teacher (UG-CEMT), for achieving state-of-the-art performance in semi-supervised medical image segmentation. UG-CEMT leverages the strengths of…
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations. However, even the largest public datasets only provide samples with pixel-level annotations for rather limited…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…
In recent years, Graph Neural Network (GNN) based models have shown promising results in simulating physics of complex systems. However, training dedicated graph network based physics simulators can be costly, as most models are confined to…
The crucial role played by the underlying symmetries of high energy physics and lattice field theories calls for the implementation of such symmetries in the neural network architectures that are applied to the physical system under…
An increasing amount of applications rely on data-driven models that are deployed for perception tasks across a sequence of scenes. Due to the mismatch between training and deployment data, adapting the model on the new scenes is often…