Project analyzes images' impact on sentiment analysis.
problem Understanding how images contribute to sentiment classification.
method Compared models using only images, only text, or both.
result Combined models improved sentiment classification accuracy.
Generates synthetic laparoscopic images for training deep neural networks.
problem Lack of large labeled data sets for laparoscopic image processing.
method Unpaired image-to-image translation to generate realistic synthetic images.
result Synthetic data set improves liver segmentation performance without manual labeling.
Novel framework uses few data for Bayesian inference in imaging.
problem Uncertainty estimation in machine learning for imaging requires large data volumes.
method Variational inference framework combining few data, domain expertise, and existing datasets.
result Bayesian models achieve state-of-the-art reconstructions with minimal data collection.
Generative model generates synthetic medical images for data augmentation and anonymization.
problem Imbalanced medical imaging data sets, especially for rare pathologies.
method Generative adversarial network (GAN) trained on two public brain MRI datasets.
result Synthetic images improve tumor segmentation performance and serve as an anonymization tool.
New method reconstructs images from fMRI data using unlabeled data.
problem Challenges in acquiring labeled data for fMRI-to-image reconstruction.
method Self-supervised training with Encoder-Decoder and Decoder-Encoder networks.
result Reconstruction network adapts to new unlabeled test data.
Satellite images improve real-estate price predictions.
problem Improving accuracy of real-estate price predictions.
method Used convolutional neural networks (CNN) to incorporate satellite image data.
result CNN model trained on satellite images and structured data performs 7% better in MAE.
New method trains image denoising models without clean reference images.
problem Training deep image denoising models without clean reference images.
method Employing networks with a 'blind spot' in the receptive field.
result Image quality is on par with state-of-the-art neural network denoisers.
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.
Adapts deep learning models trained on simulated images for use with real images.
problem Difficulty in training deep neural networks on large amounts of experimental data.
method Adversarial domain adaptation method to mitigate domain shift between simulated and experimental image data.
result Adversarial domain adaptation successfully mitigates domain shift and improves numerical observer performance.
Noise2Noise learns to restore images from noisy data alone.
problem Learning to restore images without clean data.
method Applying statistical reasoning to machine learning for image restoration using corrupted observations.
result It is possible to learn image restoration from corrupted data alone, achieving performance comparable to using clean data.
ProAGAN stabilizes GANs for learning SOMs from noisy medical imaging data.
problem Learning stochastic object models from noisy and indirect medical imaging measurements.
method Developed Progressive Growing of AmbientGANs (ProAGAN) to stabilize GANs training.
result Signal detection performance improved using ProAGAN-generated images.
Medical image reconstruction advances from sparse models to machine learning.
problem Improving image quality and reducing noise in medical imaging.
method Iterative reconstruction, modified data acquisition methods, and machine learning models.
result Machine learning methods show promise in improving image quality.
Gaudy images help train deep neural networks with less data.
problem Training deep neural networks with limited real data from visual cortex neurons.
method Used high-contrast binarized natural images (gaudy images) to train DNNs.
result Reduced training data needed for accurate DNN predictions of visual cortex neuron responses.
UNSB uses neural Schrödinger Bridge to solve unpaired image-to-image translation.
problem Difficulties in unpaired image-to-image translation with diffusion models.
method Expresses SB problem as adversarial learning problems, incorporating advanced discriminators and regularization.
result Successfully solves various unpaired image-to-image translation tasks.
A new deep learning model speeds up MRI by reconstructing from undersampled data.
problem Slow MRI due to undersampling in k-space.
method Unrolling primal-dual hybrid gradient algorithm into a deep network, gradually relaxing constraints.
result Superior MR reconstructions from highly undersampled data.
Local differential privacy method protects image privacy in machine learning.
problem Protecting image privacy in machine learning models from data owners.
method Locally perturbs image representations before releasing them to the data user.
result Proposes DCAConv, an image feature extractor that maintains high data utility while preserving privacy.
This paper addresses privacy in federated learning for medical imaging by estimating model uncertainty.
problem Privacy concerns in federated learning for medical imaging.
method Federated Learning (FL) for collaborative model training while preserving patient data privacy.
result Accurate uncertainty estimation in federated learning for medical imaging.
DreamFusion uses text-to-image diffusion models to create 3D images efficiently.
problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.
Improved image recovery with minimal data using untrained neural networks.
problem Solving inverse problems with limited data.
method Pre-training neural networks with a small number of examples to improve performance.
result Performance increases as data increases, matching generative models with less than 1% of training data.
StrokeCoder uses Transformers to generate images from single examples.
problem Creating diverse images from a single example.
method Transformer Neural Network learns from a single path-based example to generate a set of images.
result The model can generate a large set of deviated images that still represent the original image's style and concept.
GANs simulate realistic galaxy images.
problem Simulate complex astronomical images efficiently.
method Progressive GANs with Wasserstein cost function.
result Generates naturalistic galaxy images.
The paper addresses model vulnerability to image transformations.
problem Vulnerability of computer vision models to distributional shifts.
method Formulates a combinatorial optimization problem and uses search algorithms to evaluate vulnerability regions. Embeds this idea in a training procedure to define new data augmentation rules.
result Trains more robust models against distributional shifts and image manipulations.
The paper tackles interpreting DCM with image data by addressing data isomorphism.
problem Interpreting DCM with image data due to isomorphic information.
method Proposes and benchmarks two methodologies: architectural adjustments and data source mitigation.
result Direct data source mitigation is more effective for maintaining DCM's interpretability.
Method synthesizes 4D CMR images from XCAT model using GAN and SPADE.
problem Synthesizing realistic 4D CMR images with annotations and adaptable styles.
method Hybrid GAN approach with XCAT anatomical ground truth and SPADE for semantic preservation.
result Synthesized images with modality-specific features learned from real CMR data.
Augmentor adds variety to image datasets for machine learning models.
problem Improving model accuracy and generalization in machine learning.
method A high-level API for stochastic, pipeline-based image augmentation.
result Enhanced model performance through diverse image data.
Paper proposes efficient method for evaluating Bayesian models in imaging.
problem Evaluation of Bayesian models in imaging when ground truth is unavailable.
method Novel combination of Bayesian cross-validation and data fission for unsupervised model selection and misspecification detection.
result Achieved excellent selection and detection accuracy with low computational cost.
LcGAN generates synthetic CT images for hemorrhagic lesion segmentation.
problem Scarce training data for hemorrhagic lesion segmentation.
method Lesion conditional Generative Adversarial Network (LcGAN) for synthetic image generation.
result Segmentation improved by 12.8% with synthetic data augmentation.
DeepCapture detects image spam emails using CNN and data augmentation.
problem Detecting new image spam emails with overfitting.
method CNN-XGBoost framework with data augmentation.
result DeepCapture achieves an F1-score of 88%.
Generative models improve image reconstruction and uncertainty quantification.
problem Bayesian inverse problems, especially image reconstruction from noisy and incomplete data.
method Data-driven priors and computationally tractable posterior analysis.
result Efficient uncertainty quantification without retraining for different corruption types.
Modeling disease progression in brain images using monotonic Gaussian Processes.
problem Disentangling spatio-temporal disease trajectories from brain imaging data.
method Spatio-temporal matrix factorization with anatomically plausible priors, monotonic Gaussian Processes, and sparse codes.
result Monotonic Gaussian Processes model realistic disease trajectories in brain imaging data.
A multilevel model combines genetic and imaging data for AD diagnosis.
problem Classification from multimodal genetic and brain imaging data with unbalanced contributions.
method Multilevel model with structured penalties for joint effects between modalities.
result The model reveals relationships between genes, brain regions, and disease status.
Generative model learns object variability from MRI measurements.
problem Establishing stochastic object models from medical imaging data.
method Advanced AmbientGANs with multiresolution training.
result AmbientGANs reliably learn object distributions from incomplete or noisy data.
Extends pretrained models with new images and anatomy.
problem Training deep learning models from scratch with large annotated datasets is infeasible and computationally limited.
method Introduces a framework for incremental learning where new information is added iteratively while preserving representative past data.
result Increased learning capacity demonstrated through comparative evaluations on MR images.
A new method increases 3D medical image segmentation accuracy and speed.
problem Training large 3D medical images on GPUs with limited memory.
method Data-swapping method to enlarge GPU memory and avoid patching.
result Improved segmentation accuracy and speed for full-size images.
Efficiently distills pretrained text-to-image models without real data, improving FID and CLIP scores.
problem Slow iterative refinement process of diffusion-based text-to-image models.
method Guided Score identity Distillation with Long and Short Classifier-Free Guidance.
result Achieves state-of-the-art FID performance with competitive CLIP score.
A DenseNet model classifies metastatic cancer in medical images.
problem Classifying metastatic cancer in medical images efficiently and accurately.
method Proposes a DenseNet-based model for metastatic cancer classification on medical images.
result The proposed model outperformed other classical methods like Resnet34, Vgg19.
Paper develops image disguising to protect privacy in outsourced deep learning.
problem Privacy concerns in outsourced deep learning, especially re-identification and model-based attacks.
method Develops image disguising approach to protect against attacks.
result Image-disguising mechanisms provide high protection against attacks while maintaining model quality.
2DSCNs improve image data analytics by extending SCN to handle spatial information.
problem Limitation of 1D SCNs in preserving spatial information of images.
method Extend SCN to 2DSCNs by stochastically configuring hidden nodes in a matrix-inputs framework.
result 2DSCNs outperform 1D SCNs in image data analytics tasks.
New multi-layer transform models improve image denoising.
problem Improving image denoising techniques.
method Developed multi-layer transform learning algorithms.
result Multi-layer models outperform single-layer schemes in image denoising.
New model separates images into independent factors quickly and easily.
problem Separating high-dimensional data like images into independent latent factors.
method Combines bijective feature maps with linear ICA model on the Stiefel manifold.
result Models converge quickly and achieve better unsupervised latent factor discovery.
PC-RNN reconstructs MRI images from undersampled data with more details.
problem Recovering fine details from undersampled MRI data.
method Pyramid Convolutional RNN (PC-RNN) with three ConvRNN modules for multi-scale reconstruction.
result PC-RNN outperforms other methods in recovering more details from MRI images.
Proposes a probabilistic approach to semi-supervised learning using normalizing flows.
problem Leveraging unlabelled data for semi-supervised learning with limited labelled data.
method Uses a normalizing flow to learn the posterior distribution over predictions for labelled data, serving as a prior for unlabelled data.
result Demonstrates improved performance on various tasks with varying output complexity.
New methods estimate brain connectivity from calcium imaging data with missing data.
problem Estimating functional neuronal connectivity from calcium imaging data with missing data.
method Two approaches for nonparanormal Graph Quilting based on the Gaussian copula graphical model.
result Our methods yield more meaningful functional connectivity estimates than existing Gaussian graph quilting methods.
Study reveals differences in medical image models' hidden representation refinement.
problem Understanding how intrinsic dimensionality changes in neural network hidden representations across different domains.
method Analysis of 11 natural and medical image datasets using 6 network architectures.
result Medical image models refine hidden representations earlier, suggesting differences in feature abstraction.
Deep neural networks for ordinal outcomes combining image and tabular data.
problem Lack of interpretable models for ordinal outcomes in mixed data types.
method Ordinal Neural Network Transformation Models (ONTRAMs) integrating DL and classical ordinal regression.
result ONTRAMs achieve performance equivalent to standard multi-class DL models but are faster and more interpretable.
Generative Adversarial Networks optimize model parameters for image matching.
problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.
LMConv improves autoregressive models for image generation and completion.
problem Limited generation order in autoregressive models restricts their applicability.
method Introduces LMConv, a modified 2D convolution that allows arbitrary masks to be applied to weights.
result LMConv achieves improved performance on image density estimation and coherent completions.
Two-layer model sparsifies image residuals for CT image reconstruction.
problem Image reconstruction from limited and corrupted data.
method Pre-learning a two-layer sparsifying transform model with block coordinate descent optimization.
result Preliminary experiments show the two-layer model improves CT image reconstruction from low-dose measurements.