Search Results for author:
Found 25 papers, 14 papers with code
CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification
On the other hand, acquiring extensive datasets with localized labels for training is not feasible.
Contrastive Learning
Histopathological Image Classification
+2
Analyzing the Domain Shift Immunity of Deep Homography Estimation
This study explores the resilience of a variety of deep homography estimation models to domain shifts, revealing that the network architecture itself is not a contributing factor to this remarkable adaptability.
Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation
We extract snippets from the ET data by associating them with the dictation of keywords and use them to supervise the localization of specific abnormalities.
Stain Based Contrastive Co-training for Histopathological Image Analysis
Two separate CNNs are used to embed the two views into a joint feature space.
Adversarially Robust Classification by Conditional Generative Model Inversion
We propose a classification model that does not obfuscate gradients and is robust by construction without assuming prior knowledge about the attack.
Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays
The interpretability of medical image analysis models is considered a key research field.
REFLACX, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays
Furthermore, a small subset of the data contains readings from all radiologists, allowing for the calculation of inter-rater scores.
Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
To evaluate the alignment with this direction after adversarial training, we apply a metric that uses generative adversarial networks to produce the smallest residual needed to change the class present in the image.
Interpretation of Disease Evidence for Medical Images Using Adversarial Deformation Fields
The high complexity of deep learning models is associated with the difficulty of explaining what evidence they recognize as correlating with specific disease labels.
Inter-slice image augmentation based on frame interpolation for boosting medical image segmentation accuracy
We introduce the idea of inter-slice image augmentation whereby the numbers of the medical images and the corresponding segmentation labels are increased between two consecutive images in order to boost medical image segmentation accuracy.
Adversarial regression training for visualizing the progression of chronic obstructive pulmonary disease with chest x-rays
We use a conditional generative adversarial network where the generator attempts to learn to shift the output of a regressor through creating disease effect maps that are added to the original images.
Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images
Currently, most deep models for multimodal segmentation rely on paired registered images.
Combining nonparametric spatial context priors with nonparametric shape priors for dendritic spine segmentation in 2-photon microscopy images
Data driven segmentation is an important initial step of shape prior-based segmentation methods since it is assumed that the data term brings a curve to a plausible level so that shape and data terms can then work together to produce better segmentations.
Image Segmentation with Pseudo-marginal MCMC Sampling and Nonparametric Shape Priors
In this paper, we propose an efficient pseudo-marginal Markov chain Monte Carlo (MCMC) sampling approach to draw samples from posterior shape distributions for image segmentation.
Appearance invariance in convolutional networks with neighborhood similarity
We present a neighborhood similarity layer (NSL) which induces appearance invariance in a network when used in conjunction with convolutional layers.
SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation
We then propose a Bayesian model that combines the supervised and the unsupervised information for probabilistic learning.
Electron Microscopy Image Segmentation
Image Segmentation
+2
Dendritic Spine Shape Analysis: A Clustering Perspective
We perform cluster analysis on two-photon microscopic images of spines using morphological, shape, and appearance based features and gain insights into the spine shape analysis problem.
Disjunctive Normal Level Set: An Efficient Parametric Implicit Method
Level set methods are widely used for image segmentation because of their capability to handle topological changes.
Convex Decomposition And Efficient Shape Representation Using Deformable Convex Polytopes
The major contributions of this paper include a robust convex decomposition which also results in an efficient part-based shape representation, and a novel shape convexity measure.
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
Effective convolutional neural networks are trained on large sets of labeled data.
Ranked #14 on
Semi-Supervised Image Classification
on SVHN, 250 Labels
Mutual Exclusivity Loss for Semi-Supervised Deep Learning
In this paper we consider the problem of semi-supervised learning with deep Convolutional Neural Networks (ConvNets).
Unsupervised Total Variation Loss for Semi-supervised Deep Learning of Semantic Segmentation
This can be seen as a regularization term that promotes piecewise smoothness of the label probability vector image produced by the ConvNet during learning.
Image Segmentation Using Hierarchical Merge Tree
Starting with over-segmenting superpixels, we use a tree structure to represent the hierarchy of region merging, by which we reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes.
Disjunctive Normal Networks
Backpropagation, which is used to train artificial neural networks, suffers from the herd effect problem which leads to long training times and limit classification accuracy.
Scene Labeling with Contextual Hierarchical Models
At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels.
