Graph U-Nets improve graph representation learning.
problem Challenges in learning representations for graph data.
method Proposed novel graph pooling and unpooling operations in a graph U-Nets architecture.
result Graph U-Nets achieve better performance on node and graph classification tasks.
Unified framework for U-Net design and analysis.
problem Understudied design and architecture of U-Nets.
method Theoretical results, Multi-ResNets, function constraints encoding.
result Competitive and superior performance in various tasks.
U-Net trained to recover acoustic interference striations from distorted data.
problem Recovering acoustic interference striations from distorted signals.
method Training a U-Net using a random mode-coupling matrix model to generate training data.
result U-Net successfully recovers AISs under various conditions.
U-Nets use belief propagation for efficient image denoising and classification.
problem Efficiently denoise and classify images using generative hierarchical models.
method Interpreted U-Nets as implementing belief propagation in tree-structured models.
result U-Nets can efficiently approximate denoising functions with sample complexity bounds.
Researchers shrink U-Net to find limits of retinal vessel segmentation.
problem Improving retinal vessel segmentation with deep learning.
method Modified U-Net with functional blocks, then simplified to extreme conditions.
result U-Net does not degrade until very minimal configurations.
We study the use of knowledge distillation to compress the U-net architecture. We show that, while standard distillation is not sufficient to reliably train a compressed U-net, introducing other regularization methods, such as batch normalization and class re-weighting, in knowledge distillation significantly improves …
Improved U-Nets with various intermediate blocks enhance singing voice separation.
problem Improving singing voice separation accuracy using U-Net architectures.
method Implemented and compared U-Nets with different intermediate spectrogram transformation blocks.
result A specific block type achieves state-of-the-art SDR by 0.9 dB.
The paper reformulates U-Nets as wavelet-based models and applies this to hierarchical VAEs.
problem Theoretical understanding and regularization properties of U-Nets and their relationship to wavelets.
method Formulating a multi-resolution framework to identify U-Nets as finite-dimensional truncations of infinite-dimensional models, proving average pooling corresponds to projection, and identifying HVAEs as discretizations of multi-resolution diffusion processes.
result HVAEs learn a time representation allowing for improved parameter efficiency through weight-sharing.
Deep learning has shown its great promise in various biomedical image segmentation tasks. Existing models are typically based on U-Net and rely on an encoder-decoder architecture with stacked local operators to aggregate long-range information gradually. However, only using the local operators limits the efficiency and…
Wave-U-Net with MHE regularization improves singing voice separation.
problem Singing voice separation from mixed music recordings.
method Wave-U-Net architecture with MHE regularization applied to 1D filters.
result Adding MHE regularization to the loss function consistently improves singing voice separation.
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
problem Efficiently modeling long-term dependencies in sequences.
method Causal U-Net architecture with dilated filters and slow feature hypothesis.
result Seq-U-Net achieves comparable performance with speed-ups of over 4x in audio generation.
A novel 3D U-Net approach improves kidney tumor segmentation in medical imaging.
problem Challenging manual annotation and great medical impact of kidney tumor segmentation.
method End-to-end cascaded U-Nets with a localization network.
result Achieves Sørensen-Dice coefficients of 0.902 for kidney and 0.408 for tumor segmentation.
Graph convolutional networks refine organ segmentation using uncertainty analysis.
problem Challenges in organ segmentation due to variability and tissue similarity.
method Uncertainty analysis of graph convolutional networks for semi-supervised learning.
result Improved segmentation accuracy (1% for pancreas, 2% for spleen) compared to state-of-the-art methods.
Improves U-Net for scale equivariance in semantic segmentation.
problem Improving generalization in semantic segmentation tasks with varying scales.
method Introduces Scale Equivariant U-Net (SEU-Net) with carefully applied subsampling and upsampling layers and scale-equivariant layers.
result Significantly improved generalization to different scales compared to U-Net and scale-equivariant architecture without upsampling.
X-ray computed tomography (CT) using sparse projection views is a recent approach to reduce the radiation dose. However, due to the insufficient projection views, an analytic reconstruction approach using the filtered back projection (FBP) produces severe streaking artifacts. Recently, deep learning approaches using la…
White matter hyperintensity (WMH) is commonly found in elder individuals and appears to be associated with brain diseases. U-net is a convolutional network that has been widely used for biomedical image segmentation. Recently, U-net has been successfully applied to WMH segmentation. Random initialization is usally used…
In this paper, we present UNet++, a new, more powerful architecture for medical image segmentation. Our architecture is essentially a deeply-supervised encoder-decoder network where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways. The re-designed skip pathways aim at r…
3D U-Net improves kidney and tumor segmentation from CT scans.
problem Manual segmentation by clinicians is laborious and error-prone.
method Multi-scale supervised 3D U-Net with deep supervision and post-processing.
result MSS U-Net achieves high Dice coefficients (0.969 for kidney, 0.805 for tumor) on KiTS19 dataset.
GraphMix improves GNNs for semi-supervised learning.
problem Improving GNNs for semi-supervised classification.
method Parameter sharing and interpolation-based regularization.
result GraphMix improves generalization bounds and state-of-the-art performance.
A new method predicts precipitation distributions from ensemble forecasts.
problem Improving accuracy and calibration of precipitation forecasts.
method Distributional regression U-Nets for postprocessing ensemble precipitation forecasts.
result Competitive performance in continuous ranked probability score, especially for heavy precipitation.
Dual U-net models improve multi-channel MRI image reconstruction.
problem Improving MRI image reconstruction from multi-channel data.
method Two-element U-nets (W-nets) in k-space and image domains, evaluated for four configurations.
result Dual domain methods are more advantageous for simultaneous reconstruction of all channels.
Neural net reconstructs dark matter density from halo velocities.
problem Reconstructing local dark matter density from halo velocities.
method Hybrid architecture combining U-Net and DeepSets.
result Hybrid network recovers density amplitudes and phases better than U-Net.
A new method for feature fusion in U-Net decoders using difference-based gating.
problem Precise fusion of high-level semantics and low-level details in U-Net decoder reconstruction.
method Proposes two difference-based gating approaches: Feature-difference gating (FDG) and Entropy-difference gating (EDG).
result Both FDG and EDG methods outperform existing attention-based fusion methods, with EDG showing superior performance.
Sound source separation has attracted attention from Music Information Retrieval(MIR) researchers, since it is related to many MIR tasks such as automatic lyric transcription, singer identification, and voice conversion. In this paper, we propose an intuitive spectrogram-based model for source separation by adapting U-…
A new deep neural network improves mammogram image processing.
problem Improving mammogram image processing accuracy and efficiency.
method A novel deep neural network architecture with dual-path connections.
result Achieves best mammography segmentation and classification results.
Enhances Transformer for hierarchical language understanding.
problem Lack of explicit hierarchical structure in Transformer models.
method Inspired by U-Net, integrates hierarchical processing into Transformers.
result Improved performance in chit-chat dialogue tasks.
CAggNet improves medical image segmentation by fusing coarse and fine features.
problem Medical image segmentation accuracy and efficiency.
method Crossing Aggregation Network with nested skip connections and weighted aggregation.
result CAggNet achieves more accurate and efficient segmentation compared to existing methods.
Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and…
This paper explains the method used in the segmentation challenge (Task 1) in the International Skin Imaging Collaboration's (ISIC) Skin Lesion Analysis Towards Melanoma Detection challenge held in 2018. We have trained a U-Net network to perform the segmentation. The key elements for the training were first to adjust …
Traditional human activity recognition (HAR) based on time series adopts sliding window analysis method. This method faces the multi-class window problem which mistakenly labels different classes of sampling points within a window as a class. In this paper, a HAR algorithm based on U-Net is proposed to perform activity…
4-bit quantization reduces U-Net memory by 8x with minimal accuracy loss.
problem Reducing memory and computation time in deep learning models.
method Fixed-point quantization of U-Net architecture.
result 8x reduction in memory usage with minimal accuracy loss.
Advanced deep learning model improves speech enhancement by estimating phase accurately.
problem Difficulty in estimating the phase of clean speech in speech enhancement.
method Proposes Deep Complex U-Net, polar coordinate-wise complex-valued masking, and wSDR loss function.
result Achieves state-of-the-art performance in all metrics, outperforming previous approaches.
Improves audio source separation using dilated convolutions and dense connections.
problem Optimizing feature extraction in audio source separation models.
method Adaptive dilated convolutions and dense connections in U-Net architecture.
result Improved performance on MUSDB test dataset.
Proposes a new deep learning model for uncertainty quantification and propagation.
problem High-dimensional uncertainty quantification and propagation problems.
method Integrates U-net with Gaussian Gated Linear Network (GGLN) to create GLU-net.
result Less complex architecture with 44% fewer parameters than existing models.
Improved 2D cardiac MRI with less data using deep learning.
problem Reducing artefacts in undersampled 2D radial cine MRI.
method Modified U-net trained on spatio-temporal slices.
result Outperforms existing methods in image quality and training efficiency.
ST-UNet models spatio-temporal graphs by pooling and unpooling operations.
problem Lack of effective means to extract dynamic features from spatio-temporal graphs.
method Designing a multi-scale architecture, Spatio-Temporal U-Net (ST-UNet), with paired sampling operations.
result Achieves substantial improvements in spatio-temporal prediction tasks.
A new 2.5D U-net for 3D segmentation reduces memory constraints.
problem Large storage requirements for 3D convolutions in neural networks.
method Transform volumetric data into sequences of 2D images, apply 2D convolutions, and reconstruct.
result Outperforms existing methods in volumetric segmentation tasks.
Graph refinement, or the task of obtaining subgraphs of interest from over-complete graphs, can have many varied applications. In this work, we extract trees or collection of sub-trees from image data by, first deriving a graph-based representation of the volumetric data and then, posing the tree extraction as a graph …
Study develops a new tool for assessing asphalt pavement conditions using deep learning.
problem Challenges in automated pavement distress detection via road images.
method Developed a hybrid model using YOLO for classification and U-net for segmentation, creating a comprehensive pavement condition tool.
result Created a new asphalt pavement condition index using deep learning.
CNN automates vitiligo lesion segmentation quickly and accurately.
problem Manual segmentation of vitiligo lesions is time-consuming and inconsistent.
method U-Net architecture with modified contracting path, followed by watershed algorithm refinement.
result CNN achieves 73.6% Jaccard Index, significantly outperforming state-of-the-art methods.
Positron Emission Tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as Magnetic Resonance (MR) images…
Deep learning reduces artifacts in limited angle X-ray microscopy.
problem Artifacts in image reconstruction from limited angle data in TXM.
method Training a U-Net deep neural network from synthetic data to reduce artifacts.
result Significant improvement in image quality and structural similarity.
Novel 3D U-Net method for fast, reproducible white matter tract segmentation.
problem Challenges in fast and consistent white matter tract segmentation from diffusion tensor MRI.
method Convolutional neural network (3D U-Net) trained on a large DTI dataset.
result Reproducibility and accuracy of tract-specific diffusion measures.
Automated detection of MS lesions improves to 67% with 7T MRI.
problem Accurate detection of small, scarce cortical lesions in MS patients.
method 3D U-Net with brain tissue segmentation, supervised training on 7T MRI.
result 67% lesion detection rate with 42% false positives.
Deep learning improves MRI image quality from down-sampled data.
problem Improving MRI image quality from accelerated, down-sampled k-space data.
method Deep Residual Dense U-Net architecture with Residual Dense Block and new loss function.
result The proposed method achieves better performance in reconstructing high-quality images from down-sampled k-space data.
Deep learning model predicts subsurface flow dynamics.
problem Predicting dynamic subsurface flow in channelized geological systems.
method Residual U-Net and Convolutional LSTM networks trained on pressure and saturation maps.
result Surrogate model accurately predicts pressure, saturation, and well rates for new realizations.
Deep learning models reconstruct volatility surfaces from noisy data under no-arbitrage constraints.
problem Reconstructing implied volatility surfaces from sparse and noisy option quotes.
method Compared multiple neural architectures including Transformers, U-Nets, and variational autoencoders.
result Transformer and U-Net architectures achieve strong reconstruction accuracy, especially under sparse observation regimes.
We consider ill-posed inverse problems where the forward operator T is unknown, and instead we have access to training data consisting of functions fi and their noisy images Tfi. This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the t…