Related papers: Scale Equivariant U-Net
Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degradations are large-scale and low-frequency, such as wavelength-dependent colour casts and…
In recent years, convolutional neural networks (CNNs) have revolutionized medical image analysis. One of the most well-known CNN architectures in semantic segmentation is the U-net, which has achieved much success in several medical image…
Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects…
We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a…
High-resolution aerial images have a wide range of applications, such as military exploration, and urban planning. Semantic segmentation is a fundamental method extensively used in the analysis of high-resolution aerial images. However, the…
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the…
U-Net has been the go-to architecture for medical image segmentation tasks, however computational challenges arise when extending the U-Net architecture to 3D images. We propose the Implicit U-Net architecture that adapts the efficient…
Unrolled neural networks have enabled state-of-the-art reconstruction performance and fast inference times for the accelerated magnetic resonance imaging (MRI) reconstruction task. However, these approaches depend on fully-sampled scans as…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…
Conventional scaling of neural networks typically involves designing a base network and growing different dimensions like width, depth, etc. of the same by some predefined scaling factors. We introduce an automated scaling approach…
We describe generalizations of the universal approximation theorem for neural networks to maps invariant or equivariant with respect to linear representations of groups. Our goal is to establish network-like computational models that are…
Automated medical image segmentation is becoming increasingly crucial to modern clinical practice, driven by the growing demand for precise diagnosis, the push towards personalized treatment plans, and the advancements in machine learning…
In industrial defect segmentation tasks, while pixel accuracy and Intersection over Union (IoU) are commonly employed metrics to assess segmentation performance, the output consistency (also referred to equivalence) of the model is often…
Many successful learning targets such as minimizing dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond these semantic metrics, this paper aims to introduce location supervision into…
Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled…
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset as well as unlabeled target domain images to learn a…
Semi-supervised learning has gained considerable popularity in medical image segmentation tasks due to its capability to reduce reliance on expert-examined annotations. Several mean-teacher (MT) based semi-supervised methods utilize…
Deep learning has demonstrated remarkable achievements in medical image segmentation. However, prevailing deep learning models struggle with poor generalization due to (i) intra-class variations, where the same class appears differently in…
Effective feature representation is key to the predictive performance of any algorithm. This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the…
This work explores a hybrid approach to segmentation as an alternative to a purely data-driven approach. We introduce an end-to-end U-Net based network called DU-Net, which uses additional frequency preserving features, namely the…