This paper proposes a curriculum learning method for GANs using multiple discriminators.
problem Training GANs with sufficient convergence conditions and avoiding mode collapse.
method A framework for training the generator against an ensemble of discriminator networks, formalized in the full-information adversarial bandit framework.
result Our approach improves samples quality and diversity over existing baselines by effectively learning a curriculum.
Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-…
MSG-GAN stabilizes GANs by passing gradients at multiple scales.
problem Stability and adaptability of GANs to different datasets.
method Introducing MSG-GAN with multi-scale gradient flow.
result MSG-GAN converges stably on various image datasets and loss functions.
Synthesizing high resolution photorealistic images has been a long-standing challenge in machine learning. In this paper we introduce new methods for the improved training of generative adversarial networks (GANs) for image synthesis. We construct a variant of GANs employing label conditioning that results in 128x128 r…
New method trains GANs via Turing test, improving training speed and resolution.
problem Training GANs efficiently and achieving high resolution images.
method Minimizing the distance of ildep(xr)q(xf) and ildep(xf)q(xr) during training. result Succeeds on 256x256 resolution without careful hyperparameter adjustments.
We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model. This approach is in contrast with most frameworks of conditional GANs used in application today, which use the …
New unsupervised deep learning method improves temporal resolution in tMRA.
problem Limited temporal resolution in tMRA due to fixed view-sharing scheme.
method Optimal transport driven cycle-consistent generative adversarial network (cycleGAN) without fully sampled k-space reference data.
result Can generate high quality reconstructions at various temporal resolutions.
Generative adversarial networks (GAN) are improved to better estimate realness.
problem Estimating realness from multiple perspectives in GANs.
method Developed RealnessGAN, which outputs a distribution of realness.
result RealnessGAN outperforms multiple baselines and generates realistic images at high resolution.
Pairwise discriminators stabilize adversarial training by ensuring the generator's alignment is preserved.
problem Stability issues in adversarial training when using sub-optimal discriminators.
method Introducing a family of objectives using pairwise discriminators, ensuring the generator's alignment is preserved.
result Only the generator needs to converge, and the alignment is preserved with any discriminator.
SR-NAM maps low-res images to multiple high-res images realistically.
problem Mapping low-resolution images to multiple high-resolution images realistically.
method SR-NAM using Non-Adversarial Mapping (NAM) technique and a degradation model.
result Realistic degradation and down-sampling of high-resolution images.
Solves GAN mode collapse by assigning minibatches to multiple discriminators.
problem Mode collapse in GANs where models generate similar samples.
method Multiple discriminators, microbatching, and changing tasks.
result Promotes sample diversity in generated sets.
3D GAN improves MRI image quality from low-res scans.
problem Improving MRI image quality from low-resolution scans.
method Adversarial learning using 3D convolutions and least squares loss.
result 3D GAN generates high-quality 3D MRI images from low-resolution scans.
New video super-resolution method robust to multiple degradation models.
problem Current methods are not robust to mismatch between training and testing degradation models.
method Convolutional Neural Network with pseudo-inverse image formation model and perceptual losses.
result Outperforms current state-of-the-art methods and is robust to multiple degradations.
Developed AI models for multi-gas detection in near IR spectrums.
problem Detecting multiple gases in near IR spectrums.
method Used Monte Carlo KNN and multi-resolution CNN, synthesized near IR spectrums, optimized kernel sizes and channels.
result Multi-resolution CNN outperforms other models.
We present a novel approach to the formulation and the resolution of sparse Linear Discriminant Analysis (LDA). Our proposal, is based on penalized Optimal Scoring. It has an exact equivalence with penalized LDA, contrary to the multi-class approaches based on the regression of class indicator that have been proposed s…
Shows natural quasi-Poisson structure on multiplicative Grothendieck-Springer space.
problem Exploring new structures in algebraic geometry.
method Reduction along Dirac realizations.
result Natural quasi-Poisson structure exists on multiplicative Grothendieck-Springer space.
This work improves GAN training by optimizing multiple discriminator losses.
problem Training GANs with multiple discriminators using single-objective methods.
method Formulates multi-objective optimization of multiple discriminator losses.
result Hypervolume maximization outperforms previous methods in sample quality and computational cost.
HighRes-net enhances satellite imagery by fusing multiple low-res views.
problem Super-resolving satellite imagery for reliable monitoring of human impact.
method End-to-end deep learning approach for multi-frame super-resolution.
result HighRes-net outperformed in European Space Agency's MFSR competition.
Study combines expert advice to avoid discrimination without violating equalized error rates.
problem Combining expert advice to avoid discrimination without violating equalized error rates.
method Running separate instances of the classical multiplicative weights algorithm for each group.
result Even for equalized error rates, algorithms with stronger performance guarantees than multiplicative weights cannot preserve non-discrimination.
Entity resolution (ER) is the task of identifying records belonging to the same entity (e.g. individual, group) across one or multiple databases. Ironically, it has multiple names: deduplication and record linkage, among others. In this paper we survey metrics used to evaluate ER results in order to iteratively improve…
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions. Similar to the probabilistic GANs, a generator is seen as being trained to produce con…
New technique for multiple-source adaptation without density estimation.
problem Multiple-source adaptation problem.
method Discriminative technique that uses conditional probabilities from unlabeled data.
result Our technique outperforms previous generative solutions and other domain adaptation baselines.
Proposes a cross-scale residual network for multiple image restoration tasks.
problem Image restoration tasks (super-resolution, denoising, deblocking) have strong correlations.
method Cross-scale residual network exploiting scale-related features and inter-task correlations.
result Outperforms state-of-the-art methods in multiple image restoration tasks.
Framework learns surrogates for molecular dynamics across multiple time-scales.
problem Stable molecular dynamics simulations require small time-steps, but long-time-scale moments need repeated simulations.
method Implicit Transfer Operator Learning with denoising diffusion probabilistic models and SE(3) equivariant architecture.
result Models can generate self-consistent stochastic dynamics across multiple time-scales.
A new method generates graphs with hierarchical structures.
problem Generating graphs with natural hierarchical structures.
method Recursively generates community structures at multiple resolutions, parallel generation of all sub-structures.
result Improves generative performance on multiple graph datasets.
WrapNet optimizes inference for low-resolution neural networks by using 8-bit additions.
problem Reducing multiplication complexity in low-resolution neural networks.
method Adapting neural networks to use low-resolution (8-bit) additions in accumulators, with a cyclic activation layer and overflow penalty regularizer.
result Achieves comparable classification accuracy to 32-bit counterparts using low-resolution additions.
Proposes a model to handle mobile health data with irregular measurements.
problem Handling heterogeneous, multi-resolution data in mobile health.
method Individualized dynamic latent factor model for irregular multi-resolution time series data.
result Superior performance compared to existing methods in simulation and smartwatch data applications.
Develops a multi-resolution multi-task framework for integrating noisy, varying data.
problem Integrating evidence from multiple observation processes with varying resolutions and noise levels.
method Multi-resolution Multi-task Gaussian Processes (MRGP) framework, shallow and deep Gaussian Process mixtures.
result Generalizes and outperforms state-of-the-art GP compositions, offering efficient corrections and approximations.
ElbowSig assesses clustering structure at multiple scales.
problem Selecting optimal number of clusters in unsupervised learning.
method Formalizes elbow heuristic with a normalized discrete curvature statistic.
result Validates multiscale clustering structure over various resolutions.
DoPaNet uses multiple discriminators to prevent mode collapse in GANs.
problem Mode collapse in adversarial training.
method Employing multiple discriminators and a classifier to guide the generator.
result DoPaNet effectively covers the target distribution and outperforms competing methods.
The paper proposes a method to improve fine-resolution predictions using coarse-resolution data.
problem Limited supervision for fine-resolution predictions with scarce data.
method Attention-based regularization on multi-view coarse-resolution data.
result The method improves fine-resolution predictions using coarse-resolution data.
Principal component analysis (PCA) is widely used for feature extraction and dimensionality reduction, with documented merits in diverse tasks involving high-dimensional data. Standard PCA copes with one dataset at a time, but it is challenged when it comes to analyzing multiple datasets jointly. In certain data scienc…
Recent advances in video super-resolution have shown that convolutional neural networks combined with motion compensation are able to merge information from multiple low-resolution (LR) frames to generate high-quality images. Current state-of-the-art methods process a batch of LR frames to generate a single high-resolu…
Proposes KMvDA for object recognition from multi-view data.
problem Recognizing objects from different views, even when views are heterogeneous.
method Introduces kernel multi-view discriminant analysis (KMvDA) and uses random Fourier features (RFF) for large-scale learning.
result KMvDA and RFF approximation improve object recognition from multi-view data.
Proves representability of complex semigroup systems.
problem Representability of systems of proportionally modular numerical semigroups.
method Canonical equivariant resolution of weighted homogeneous surface singularities.
result Every system of proportionally modular numerical semigroups is representable.
Explains LDA and QDA for binary and multiple classes.
problem Classification methods in statistical and probabilistic learning.
method Optimization of decision boundaries, estimation of parameters, relation to other methods.
result Equivalence of LDA and Fisher discriminant analysis.
A deep learning framework learns meaningful representations for weakly supervised multiple instance learning.
problem Weakly supervised multiple instance learning with uncertainty in positive instance labels.
method Discriminative model regularized by variational autoencoders to learn latent representations.
result Improved performance on standard benchmark datasets compared to state-of-the-art approaches.
This paper simplifies diffusion models for high resolution images.
problem Applying diffusion models to high resolution images is challenging.
method Adjust noise schedule, scale specific parts, add dropout, and use downsampling.
result Achieved state-of-the-art image generation performance.
Paper proposes distributed sparse multicategory discriminant analysis for classification.
problem Sparse multicategory classification with distributed data.
method Convex formulation, distributed setting, invariant discriminant subspace recovery.
result Distributed sparse multicategory linear discriminant analysis performs as good as centralized version after a few rounds of communications.
Sparse representations using overcomplete dictionaries have proved to be a powerful tool in many signal processing applications such as denoising, super-resolution, inpainting, compression or classification. The sparsity of the representation very much depends on how well the dictionary is adapted to the data at hand. …
We propose a new approach to train the Generative Adversarial Nets (GANs) with a mixture of generators to overcome the mode collapsing problem. The main intuition is to employ multiple generators, instead of using a single one as in the original GAN. The idea is simple, yet proven to be extremely effective at covering …
Factorial moments are convenient tools in nuclear physics to characterize the multiplicity distributions when phase-space resolution (Δ) becomes small. For uncorrelated particle production within Δ, Gaussian statistics holds and factorial moments Fq are equal to unity for all orders q. Correlations between par…
IntroVAE synthesizes high-quality photos by self-evaluating and improving its outputs.
problem Generating high-quality photographic images with stable and realistic results.
method Introspective Variational Autoencoder (IntroVAE) that trains inference and generator models jointly, encouraging the inference model to distinguish between generated and real samples.
result Produces high-resolution photo-realistic images comparable to or better than state-of-the-art GANs.
Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-res…
Enhances hashing for cross-modal retrieval using multi-view features.
problem Limited improvement in single-view hashing for cross-modal retrieval.
method Exploits multiple views to enrich feature information, learning discriminative hash codes.
result Superior performance compared to state-of-the-art methods on various datasets.
The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolu…
We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize…
DeepAM optimizes deep neural networks for image super-resolution.
problem Image super-resolution using deep neural networks.
method L-layer analysis dictionary model with IPAD and CAD.
result DeepAM outperforms deep neural networks with back-propagation.