BNCR-GAN improves GANs to generate clean images from degraded inputs.
problem Generating clean images from blurred, noisy, and compressed degraded inputs.
method Multiple-generator model with image, blur-kernel, noise, and quality-factor generators, using masking architectures and adaptive consistency losses.
result BNCR-GAN effectively learns clean image generators from degraded images without degradation parameters.
SVD-RND detects blurred images better than conventional methods.
problem Blurred images can fool conventional OOD detection schemes.
method Constructs a novel RND-based detector that uses blurred images during training.
result SVD-RND outperforms baseline detectors in various domains.
The mean-shift algorithm is a popular algorithm in computer vision and image processing. It can also be cast as a minimum gamma-divergence estimation. In this paper we focus on the "blurring" mean shift algorithm, which is one version of the mean-shift process that successively blurs the dataset. The analysis of the bl…
f-VAEs improve VAEs by generating clearer images and are more efficient.
problem Blurred images generated by VAEs.
method Integrating VAEs and flow-based models (conditional flows).
result f-VAEs generate clearer images and achieve the same performance with smaller architecture.
This paper presents a learning method for convolutional autoencoders (CAEs) for extracting features from images. CAEs can be obtained by utilizing convolutional neural networks to learn an approximation to the identity function in an unsupervised manner. The loss function based on the pixel loss (PL) that is the mean s…
Bayesian detector improves defect detection on rough surfaces.
problem Defect detection on motion blurred images with rough texture.
method Developed Bayesian detector using reflected non-local prior distributions.
result Significantly enhanced accuracy in identifying defects.
Paper tackles image recovery from blurry measurements using deep generative priors.
problem Jointly recovering two real-valued signals from phaseless circular convolutions.
method Alternating gradient descent algorithm with deep generative priors.
result Reconstructs quality images from blurry measurements.
Blind deconvolution involves the estimation of a sharp signal or image given only a blurry observation. Because this problem is fundamentally ill-posed, strong priors on both the sharp image and blur kernel are required to regularize the solution space. While this naturally leads to a standard MAP estimation framework,…
A natural way to characterize the cluster structure of a dataset is by finding regions containing a high density of data. This can be done in a nonparametric way with a kernel density estimate, whose modes and hence clusters can be found using mean-shift algorithms. We describe the theory and practice behind clustering…
New blurring diffusion models bridge heat dissipation and denoising.
problem Developing a new generative modeling approach.
method Connecting blurring to Gaussian diffusion with non-isotropic noise.
result Proposed Blurring Diffusion Models offer the best of both Gaussian denoising and inverse heat dissipation.
AR-GANs learn depth and DoF from unlabeled images using aperture rendering and focus cues.
problem Learning depth and DoF from unlabeled natural images with diverse viewpoints and shapes.
method Aperture rendering and focus cues to learn depth and DoF from unlabeled images.
result AR-GANs effectively learn depth and DoF from various datasets, including flower, bird, and face images.
Enhances deep networks robustness with data mollification and label smoothing.
problem Improving deep neural networks' robustness against corruptions.
method Coupling data mollification (image noising and blurring) with label smoothing.
result Improved robustness and uncertainty quantification on corrupted image benchmarks.
Deep convolutional neural networks (CNNs) based approaches are the state-of-the-art in various computer vision tasks, including face recognition. Considerable research effort is currently being directed towards further improving deep CNNs by focusing on more powerful model architectures and better learning techniques. …
New method relaxes TV distance for two-sample testing without distributional assumptions.
problem Challenges in certifying equality or providing tight bounds on TV distance for two distributions.
method Examined blurred total variation distance, a relaxation of TV distance.
result Provided theoretical guarantees for upper and lower bounds on blurred TV distance.
Neural network estimates rigid motion in stroke imaging to improve image quality.
problem Rigid patient motion during C-arm CBCT imaging reduces image quality.
method Neural network trained to regress reprojection error based on image information.
result Neural network outperforms entropy-based method in motion estimation.
Hyperspectral remote sensing images (HSIs) usually have high spectral resolution and low spatial resolution. Conversely, multispectral images (MSIs) usually have low spectral and high spatial resolutions. The problem of inferring images which combine the high spectral and high spatial resolutions of HSIs and MSIs, resp…
Generative models improve image classifier explanations by realistically removing features.
problem Perturbation-based explanations often produce unrealistic counterfactual samples.
method Integrate generative inpainters into attribution methods to remove input features.
result Improved explanation methods in object localization, deletion, and saliency metrics.
Improved CNN with general image processing kernels reduces training time and achieves high accuracy.
problem Training time and accuracy of CNNs.
method Used 41 general-purpose kernels for the first layer of CNNs.
result GFNN reduces training time by 30% and achieves 99.56% accuracy.
We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a qu…
BlurNet defends against adversarial attacks by filtering feature maps.
problem Adversarial attacks on deep neural networks, especially for image classification.
method BlurNet introduces a depthwise convolution layer with standard blur kernels after the first layer to filter high frequency noise.
result The defense reduces the success rate of adversarial attacks from 90% to 20% with total variation regularization.
A new distance metric derived from information theory and estimation theory.
problem Developing a robust distance metric for complex signal distributions.
method Information-Estimation Metric (IEM) derived from continuous probability density and denoising errors.
result The IEM is a valid global distance metric that adapts to the geometry of complex distributions.
Paper explores unsupervised learning for ultrasound image artifact removal.
problem Improving visual quality of ultrasound images from various artifacts.
method Inspired by optimal transport cycleGAN, unsupervised deep learning for artifact removal.
result Unsupervised learning method provides comparable results to supervised learning.
A new image interpolation model using sparse representation and nonlocal linear regression.
problem Image interpolation without blurring and noise.
method Sparse representation, nonlocal self-similarity, nonlocal linear regression, adaptive sub-dictionary learning, weighted encoding.
result Our method outperforms state-of-the-art methods in quantitative measures and visual quality.
Contrastive learning recovers latent distributions for ambiguous inputs, including aleatoric uncertainty.
problem Real-world observations often have inherent ambiguities, making the true posterior probabilistic with heteroscedastic uncertainty.
method Extended InfoNCE objective and encoders to predict latent distributions, proving they recover the correct posteriors, including aleatoric uncertainty.
result Contrastive learning encoders can recover the correct posteriors of data-generating processes, including aleatoric uncertainty, up to a rotation of the latent space.
A test confirms if a local maximum is globally optimal in imaging problems.
problem Confirming if a local maximum is globally optimal in imaging problems.
method Reparameterizing the likelihood function to embed its domain into a higher dimensional parameter space.
result Improved accuracy and reduced computation for camera-blur estimation.
Hyperspectral remote sensing images (HSIs) are characterized by having a low spatial resolution and a high spectral resolution, whereas multispectral images (MSIs) are characterized by low spectral and high spatial resolutions. These complementary characteristics have stimulated active research in the inference of imag…
Confidence intervals improve evaluation of binary prediction rules in data mining.
problem Uncertainty in performance measures estimation from finite datasets.
method Asymptotic normal approximations for confidence intervals, with a blurring correction.
result Improved finite sample coverage probabilities and general performance measures inference.
Noise is an inherent issue of low-light image capture, one which is exacerbated on mobile devices due to their narrow apertures and small sensors. One strategy for mitigating noise in a low-light situation is to increase the shutter time of the camera, thus allowing each photosite to integrate more light and decrease n…
Deep learning boosts micro-CT image resolution and texture recovery.
problem Compensating for image resolution trade-offs in micro-CT imaging.
method EDSRGAN trained on a diverse dataset of uCT images.
result EDSRGAN outperforms other methods in texture recovery and resolution.
This paper highlights new opportunities for designing large-scale machine learning systems as a consequence of blurring traditional boundaries that have allowed algorithm designers and application-level practitioners to stay -- for the most part -- oblivious to the details of the underlying hardware-level implementatio…
Combined ML and JVC-SENSE enable high-resolution imaging with fewer shots and less distortion.
problem Severe distortion artifacts and blurring in high-resolution imaging due to shot-to-shot variations in msEPI.
method Employed deep learning to obtain an interim image with minimal artifacts, which was then used in a Joint Virtual Coil Sensitivity Encoding (JVC-SENSE) reconstruction.
result Enabled navigator-free, highly accelerated multishot EPI with fewer shots and improved geometric fidelity.
Physen-Noise2Noise tackles defocus deblurring in low-light conditions with physics-guided self-supervised learning.
problem Defocus deblurring in low-light conditions with complex biased noise.
method Physics-guided self-supervised deblurring framework that leverages noisy multi-frame observations and a learnable noise bias parameter.
result Physen-Noise2Noise consistently outperforms state-of-the-art methods in defocus deblurring with complex biased noise.
Bayesian image reconstruction using pre-trained generative models.
problem Distribution shifts and latent variable changes in image data.
method Combining SOTA generative models with Bayes' theorem for image restoration tasks.
result Competitive performance on super-resolution and in-painting tasks without training.
GWHD dataset offers 4,700 high-res images of wheat heads.
problem Challenges in wheat head detection from high-resolution imagery.
method Large, diverse dataset with detailed metadata.
result Benchmark for wheat head detection methods.
Enhances neural network robustness with Mixup and TLAT.
problem Neural networks are sensitive to various perturbations and adversarial examples.
method Combines Mixup augmentation with Targeted Labeling Adversarial Training (TLAT).
result M-TLAT increases robustness against 19 corruptions and 5 adversarial attacks without reducing clean sample accuracy.
New method recovers compressed crack images for automatic segmentation.
problem Recover crack images from compressed data for SHM systems.
method Generative model-based CS method for crack images.
result Generative model effectively captures crack features for segmentation.
Improves VAE by adding a softmax classifier to enhance mutual information.
problem Posterior collapse and blurred reconstructions in VAE.
method Integrates an auxiliary softmax multi-classifier to improve VAE training.
result VAE-AS significantly improves mutual information and solves posterior collapse.
Improved model robustness against corruptions using online adaptation.
problem Machine vision models' vulnerability to image corruptions like blurring or compression artefacts.
method Using corrupted images' statistics for unsupervised online adaptation to improve robustness.
result ResNet-50 achieves 62.2% mCE on ImageNet-C with adaptation, improving from 76.7% without.
Self-supervised method enhances ultrasound images without needing clean targets.
problem Multiplicative speckle, acquisition blur, and scanner artifacts hamper ultrasound interpretation.
method Physics-guided degradation model trained on rotated/cropped patches with synthesized inputs.
result Achieves highest PSNR/SSIM across Gaussian and speckle noise levels, with significant improvements in heavy noise conditions.
Paper shows linear convergence of ISTA and FISTA for ill-conditioned images.
problem Solving linear inverse problems with sparse representation in signal and image processing.
method Revisits iterative shrinkage-thresholding algorithms (ISTA) and improves their convergence properties.
result Linear convergence of ISTA and FISTA for strongly convex smooth parts, even in ill-conditioned cases.
HypeGBMS clusters data in hyperbolic space, overcoming Euclidean limitations.
problem Clustering in hierarchical or tree-like datasets in curved spaces.
method Hyperbolic Gaussian Blurring Mean Shift with Möbius-weighted means.
result HypeGBMS effectively captures latent hierarchies in non-Euclidean data.
This paper presents a natural extension of stagewise ranking to the the case of infinitely many items. We introduce the infinite generalized Mallows model (IGM), describe its properties and give procedures to estimate it from data. For estimation of multimodal distributions we introduce the Exponential-Blurring-Mean-Sh…
RBMs learn archetypes when trained on blurred copies of them, revealing a critical sample size.
problem Determining the critical sample size for RBMs to learn archetypes.
method Formal equivalence between RBMs and Hopfield networks, statistical-mechanics of disordered systems, Monte Carlo simulations.
result A phase diagram highlights regions where learning can be accomplished.
Debiased Wasserstein barycenters improve on entropy regularization in OT.
problem Entropy regularization in OT introduces bias, leading to blurred barycenters.
method Propose debiased Wasserstein barycenters using Sinkhorn iterations.
result Debiased barycenters preserve fast Sinkhorn-like iterations without entropy smoothing bias.
PDA improves deep neural networks' robustness against adversarial and common corruptions.
problem Deep neural networks' lack of robustness against common corruptions and adversarial attacks.
method Progressive Data Augmentation (PDA) that injects diverse adversarial noises during training.
result PDA-trained networks are more robust against both adversarial and common corruptions.
We present the first public release of our generic neural network training algorithm, called SkyNet. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as…
Spatial smoothing improves BNNs' accuracy, uncertainty, and robustness without increasing computational cost.
problem Large ensembles in BNNs increase computational cost and reduce performance.
method Spatial smoothing adds blur layers to convolutional neural networks to ensemble neighboring feature map points.
result Spatial smoothing improves BNNs' performance with fewer ensembles and enhances robustness.
New method for manifold fitting under unbounded noise.
problem Noise blurs tangent space estimation, leading to inaccurate manifold recovery.
method Directly estimate tangent spaces at projected points on the manifold, not at sample points.
result Theoretical convergence in high probability for upper bound of manifold distance.