Search Results for author:
Found 17 papers, 3 papers with code
Unpaired Translation from Semantic Label Maps to Images by Leveraging Domain-Specific Simulations
We introduce a contrastive learning framework for generating photorealistic images from simulated label maps, by learning from unpaired sets of both.
Generative Feature-driven Image Replay for Continual Learning
In this work, we propose Genifer (GENeratIve FEature-driven image Replay), where a generative model is trained to replay images that must induce the same hidden features as real samples when they are passed through the classifier.
Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images
Interactive simulation of ultrasound imaging greatly facilitates sonography training.
Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps
We herein propose a deep learning-based cell detection framework that can operate on large microscopy images and outputs desired probabilistic predictions by (i) integrating Bayesian techniques for the regression of uncertainty-aware density maps, where peak detection can be applied to generate cell proposals, and (ii) learning a mapping from the numerous proposals to a probabilistic space that is calibrated, i. e. accurately represents the chances of a successful prediction.
Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers
However, for combinations that do not exist in a labeled training dataset, one cannot have any estimation of potential segmentation quality if that combination is encountered during inference.
Learning Ultrasound Rendering from Cross-Sectional Model Slices for Simulated Training
Given the high level of expertise required for navigation and interpretation of ultrasound images, computational simulations can facilitate the training of such skills in virtual reality.
Modality Attention and Sampling Enables Deep Learning with Heterogeneous Marker Combinations in Fluorescence Microscopy
Quantitative characterization of structures in acquired images often relies on automatic image analysis methods.
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
Inspired by recent advances in natural texture synthesis, we train deep neural models to generate textures by non-linearly combining learned noise frequencies.
Deep Image Translation for Enhancing Simulated Ultrasound Images
To incorporate anatomical information potentially lost in low quality images, we additionally provide segmentation maps to image translation.
Learning Generative Models using Denoising Density Estimators
Learning probabilistic models that can estimate the density of a given set of samples, and generate samples from that density, is one of the fundamental challenges in unsupervised machine learning.
Ranked #1 on
Density Estimation
on UCI MINIBOONE
Smart, Deep Copy-Paste
In this work, we propose a novel system for smart copy-paste, enabling the synthesis of high-quality results given a masked source image content and a target image context as input.
Learning to Take Directions One Step at a Time
Because items in an image can be animated in arbitrarily many different ways, we introduce as control signal a sequence of motion strokes.
Understanding Degeneracies and Ambiguities in Attribute Transfer
We study the problem of building models that can transfer selected attributes from one image to another without affecting the other attributes.
Specular-to-Diffuse Translation for Multi-View Reconstruction
To alleviate this restriction, we introduce S2Dnet, a generative adversarial network for transferring multiple views of objects with specular reflection into diffuse ones, so that multi-view reconstruction methods can be applied more effectively.
FaceShop: Deep Sketch-based Face Image Editing
We present a novel system for sketch-based face image editing, enabling users to edit images intuitively by sketching a few strokes on a region of interest.
Disentangling Factors of Variation by Mixing Them
We learn our representation without any labeling or knowledge of the data domain, using an autoencoder architecture with two novel training objectives: first, we propose an invariance objective to encourage that encoding of each attribute, and decoding of each chunk, are invariant to changes in other attributes and chunks, respectively; second, we include a classification objective, which ensures that each chunk corresponds to a consistently discernible attribute in the represented image, hence avoiding degenerate feature mappings where some chunks are completely ignored.
Challenges in Disentangling Independent Factors of Variation
Such models could be used to encode features that can efficiently be used for classification and to transfer attributes between different images in image synthesis.
