A new loss function for VAEs improves image quality and efficiency.
problem Training VAEs to generate realistic images requires a loss function that reflects human perception.
method Based on Watson's perceptual model, the loss function computes a weighted distance in frequency space, accounts for luminance and contrast masking, and is extended to color images.
result VAEs trained with the new loss function generated high-quality, less blurry images with fewer artifacts and less computational resources.
Transmission imaging, as an important imaging technique widely used in astronomy, medical diagnosis, and biology science, has been shown in [49] quite different from reflection imaging used in our everyday life. Understanding the structures of images (the prior information) is important for designing, testing, and choo…
DeepBrain learns functional neural image representations for gene ontology classification.
problem Classifying gene ontology categories from neural in-situ hybridization images.
method Uses deep convolutional denoising autoencoders (CDAE) to generate compact, invariant representations.
result Improves classification accuracy by 75% to 0.98 AUC.
A new image representation method using hypernetworks.
problem Representing images in a way that allows for continuous manipulation and analysis.
method Constructing a hypernetwork that maps pixel positions to colors, allowing for continuous image manipulation.
result Comparable image super-resolution results to existing methods using a single model.
Recurrent iterated function systems (RIFSs) are improvements of iterated function systems (IFSs) using elements of the theory of Marcovian stochastic processes which can produce more natural looking images. We construct new RIFSs consisting substantially of a vertical contraction factor function and nonlinear transform…
Proposes a deep neural network approach for image response regression.
problem Associations between medical images and covariates.
method Spatially varying coefficient models with deep neural networks.
result Explicitly accounts for spatial smoothness and subject heterogeneity.
Extends image-to-image translation to multiple distributions, allowing composite functions.
problem Limited to single pair translations, new mechanism scalable to multiple distributions.
method Decoupled training mechanism for multiple distributions, composite translation functions.
result Generates images with characteristics not seen in training set.
Proposes a new loss function for deep learning image segmentation.
problem Efficiency and reliance on labeled data in deep learning image segmentation.
method Mumford-Shah functional adapted for deep learning.
result Improves efficiency and effectiveness of deep learning for image segmentation.
Optimally registers and clusters joint images using multivariate information.
problem Joint image registration and clustering in limited-resolution images.
method Asymptotically optimal algorithms based on multivariate information functionals.
result Order-optimal registration and clustering of numerous images.
A new pyramidal diffusion model speeds up image generation.
problem Training and evaluating diffusion models are time-consuming.
method Introduces a pyramidal diffusion model with a single score function.
result Generates high-resolution images from low-resolution starting points efficiently.
Estimation of response functions is an important task in dynamic medical imaging. This task arises for example in dynamic renal scintigraphy, where impulse response or retention functions are estimated, or in functional magnetic resonance imaging where hemodynamic response functions are required. These functions can no…
Paper proposes a new loss function to improve image reconstruction quality.
problem Blurred images when using pixel loss for convolutional autoencoders.
method Introduces spatial frequency loss (SFL) to mitigate blurring.
result Reduced blurs in reconstructed images using SFL.
A new method classifies images using a compressed summary.
problem Classifying images efficiently.
method Compressive learning with a novel sketch function.
result Improved image classification with less data.
Convolutional neural networks handle rotated image symmetries without dimensionality issues.
problem Binary image classification with rotational symmetry.
method Least squares plug-in classifiers based on convolutional neural networks under rotationally symmetric assumptions.
result Convolutional neural networks can circumvent the curse of dimensionality in binary image classification with rotational symmetry.
Generative models improve image probability estimation but lack interpretability.
problem Lack of interpretability in generative models for natural image distributions.
method Extracted explicit probability density estimates from GANs and analyzed latent representations.
result Natural image density functions are difficult to interpret.
Proposes adversarial normalization for multi-domain image segmentation.
problem Current image normalization is per-dataset, limiting multi-domain segmentation.
method Adversarial training to learn common normalizing functions across multiple datasets.
result Optimal normalizer improves segmentation accuracy and realism.
Paper presents a method to detect out-of-distribution spectra in intra-operative functional imaging.
problem Detecting out-of-distribution (OoD) spectra in multispectral optical imaging during surgery.
method Information theory-based approach using WAIC with an ensemble of INNs.
result The method is effective in detecting OoD spectra, improving the reliability of functional imaging.
EdgeFool generates adversarial images to mislead classifiers.
problem Misleading classifiers with adversarial images.
method Trains a fully convolutional neural network to generate perturbations that enhance image details and mislead classifiers.
result EdgeFool outperforms other adversarial methods on various classifiers and datasets.
A new adaptive binarization technique using fuzzy integrals improves image quality.
problem Improving image thresholding quality.
method FLAT (Fuzzy Local Adaptive Thresholding) based on fuzzy integrals.
result The proposed FLAT method produces better image quality than traditional algorithms and neural networks.
Automatically computes reference ranges for UK Biobank cardiac data.
problem Improving healthcare by discovering patterns in large-scale population data.
method Fully automatic pipeline for 3D cardiac MR image analysis.
result Statistically significant agreement between manual and automatic indexes.
This research improves DNN defense by profiling and analyzing effective paths.
problem Defending against adversarial attacks on deep neural networks.
method Profiling DNN models into functional blocks and aggregating per-image effective paths to class-level effective paths.
result Adversarial images activate different effective paths from normal images.
Survey of deep learning methods for fMRI natural image reconstruction.
problem Reconstructing natural images from fMRI brain activity.
method Survey of deep learning approaches, including architectural design, datasets, and evaluation metrics.
result Performance evaluation across standardized metrics.
R-PLS improves analysis of brain functional connectivity matrices.
problem Improving analysis of functional connectivity matrices in brain imaging.
method Introducing R-PLS, a generalization of PLS for symmetric positive definite matrices.
result R-PLS identifies key functional connections in brain imaging datasets.
Paper reduces Hausdorff Distance in medical image segmentation.
problem Reduction of Hausdorff Distance in medical image segmentation.
method Three novel loss functions for training CNNs to estimate and reduce HD.
result Approximately 18-45% reduction in HD without degrading other performance metrics.
DNNs can approximate fractal functions with exponential linear regions.
problem Understanding neural network approximations of complex functions.
method Using Iterated Function Systems (IFS) and neural networks to generate fractal functions.
result DNNs can generate fractal functions with a number of linear regions exponential in the number of parameters.
CapsuleGAN uses capsule networks in GANs for better image data modeling.
problem Improving image data modeling in GANs.
method CapsuleGAN uses capsule networks as discriminators in GANs, with a new objective function incorporating margin loss.
result CapsuleGAN outperforms standard GANs on image data modeling and semi-supervised classification.
This work improves deep learning models for fMRI by generating realistic brain morphology images.
problem Limited dataset sizes for functional MRI limit the accuracy of deep learning models.
method Proposes a method to generate new fMRI images with realistic brain morphology.
result Demonstrates a 26% improvement in predicting antidepressant treatment response using augmented images.
Due to advances in sensors, growing large and complex medical image data have the ability to visualize the pathological change in the cellular or even the molecular level or anatomical changes in tissues and organs. As a consequence, the medical images have the potential to enhance diagnosis of disease, prediction of c…
Improved VAE model enhances image accuracy and robustness.
problem Enhancing accuracy and robustness of VAE models.
method Coupled VAE method with generalized entropy function.
result Improved accuracy and robustness of output images.
A new framework uses information theory to detect anomalies in images without labeled data.
problem Detect anomalies in images without labeled data.
method A direct objective function using information theory to maximize the distance between normal and anomalous data.
result The proposed framework significantly outperforms state-of-the-arts on multiple benchmark datasets.
Improved analysis of calcium imaging data with higher SNR and compression.
problem Challenges in analyzing large-scale calcium imaging datasets.
method Spatially-localized penalized matrix decomposition (PMD) for denoising and compression.
result Significant improvement in SNR and compression rates with minimal signal loss.
Proposes a unified normalization method for multi-domain medical images.
problem Inadequate joint information across multiple datasets hinders image segmentation performance.
method Adversarial and task-driven normalization approach to learn a common normalizing function across multiple datasets.
result Jointly normalized images improve segmentation accuracy by up to 57.5%.
An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approac…
Improves discrete latent representations using differentiable approximation bridges.
problem Improving discrete latent representations in neural networks.
method Training with a differentiable approximation bridge (DAB) neural network.
result Improves state-of-the-art performance in various domains.
New image restoration method using localized patches and external databases.
problem Image restoration challenges.
method Localized structured prediction and non-linear multi-task learning for optimizing a penalized energy function.
result Strong statistical guarantees and practical effectiveness demonstrated on various image restoration problems.
DRSVM uses deep learning to rank relative attributes between image pairs.
problem Classifying relative attributes between image pairs.
method Deep Siamese network with rank SVM loss function.
result DRSVM outperforms state-of-the-art methods on multiple datasets.
Machine learning detects subhalos in lensed images with high accuracy and low false positives.
problem Detecting substructure in strongly lensed images.
method Developed a neural network for image segmentation to locate and mass estimate subhalos.
result The network can detect subhalos with masses m≳108.5M⊙ and measure the subhalo mass function. ENSURE framework trains deep image recon algorithms without clean data.
problem Lack of clean, fully sampled ground-truth data for deep learning image reconstruction.
method Introduces ENSURE framework, a generalization of SURE and GSURE to random sampling patterns.
result ENSURE loss function is an unbiased estimate for true mean-square error.
Develops a robust method for image reconstruction from limited data.
problem Inference of unknown images from few measurements, often ill-posed.
method Introduces DPnP, a diffusion plug-and-play method combining likelihood and score-based samplers.
result Establishes performance guarantees for DPnP, demonstrating robustness and efficiency.
Paper tackles conditional learning between different domains.
problem Learning conditional distribution between input and output domains.
method Cooperative training of fast and slow thinking models.
result Jointly trained models improve conditional learning tasks.
We discretize a cost functional for image registration problems by deriving Taylor expansions for the matching term. Minima of the discretized cost functionals can be computed with no spatial discretization error, and the optimal solutions are equivalent to minimal energy curves in the space of k-jets. We show that t…
We propose and analyze a constrained level-set method for semi-automatic image segmentation. Our level-set model with constraints on the level-set function enables us to specify which parts of the image lie inside respectively outside the segmented objects. Such a-priori information can be expressed in terms of upper a…
A new method for image annotation using multiview Hessian regularization.
problem Semi-supervised learning biases towards a constant function and is limited to single view data.
method Develops multiview Hessian regularization (mHR) to handle multiview data and improve generalization.
result mHR optimally combines multiple Hessian regularizations from different views to steer the classification function.
Improves text-to-image generation with bidirectional capabilities.
problem Generating realistic images from text descriptions.
method Integrates text and image modalities using MMVR architecture with n-gram cost function and multiple sentences.
result Significant improvement in image quality over existing methods (over 20%).
Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…
New method uses contours of segmented images for X-ray classification.
problem Classifying X-ray images of segmented radiography.
method Develops a new approach for image analysis of multivariate planar curves, addressing alignment issues.
result Demonstrates the robustness and appeal of the proposed method through detection of cardiomegaly and numerical experiments.
Neural network iteratively refines image registration, achieving compactness and speed.
problem Non-compact representation of deformations in image registration.
method Recurrent registration neural network that computes local deformations iteratively.
result Our method achieves similar accuracy but is more compact and faster.
A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.
problem Improving perceptual quality and distributional alignment of samples from conditional diffusion models.
method Learned continuous guidance weights ωc,(s,t) are used to minimize distributional mismatch and reward guided sampling. result Improvements in Fréchet inception distance (FID) for image generation and better image-prompt alignment in text-to-image applications.