Search Results for author:
Found 43 papers, 22 papers with code
Deep Ordinal Regression Network for Monocular Depth Estimation
These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions.
Ranked #13 on
Depth Estimation
on NYU-Depth V2
CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
Nonparametric Spherical Topic Modeling with Word Embeddings
In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere.
Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping
Unsupervised domain mapping aims to learn a function to translate domain X to Y by a function GXY in the absence of paired examples.
Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation
The first one lets T compete with G to achieve maximum perturbation.
Context Matters: Graph-based Self-supervised Representation Learning for Medical Images
Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context.
Twin Auxiliary Classifiers GAN
One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier.
Ranked #2 on
Conditional Image Generation
on CIFAR-100
Twin Auxilary Classifiers GAN
One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN) that generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier.
Ranked #2 on
Image Generation
on CIFAR-100
Can contrastive learning avoid shortcut solutions?
However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i. e., by inadvertently suppressing important predictive features.
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image.
Self-Supervised Vessel Enhancement Using Flow-Based Consistencies
Our experiments on various public datasets in 2D and 3D show that our method performs better than unsupervised methods while learning useful transferable features from unlabeled data.
Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple
We propose novel finite-dimensional spaces of R - R transformations, n [?]
Explanation by Progressive Exaggeration
As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical.
Anatomy-Guided Weakly-Supervised Abnormality Localization in Chest X-rays
The critical component in our framework is an anatomy-guided attention module that aids the downstream observation network in focusing on the relevant anatomical regions generated by the anatomy network.
Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut.
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc.
Semi-Supervised Hierarchical Drug Embedding in Hyperbolic Space
We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the knowledge-based drug-drug similarity to induce the clustering of drugs in hyperbolic space.
Robust Angular Local Descriptor Learning
In recent years, the learned local descriptors have outperformed handcrafted ones by a large margin, due to the powerful deep convolutional neural network architectures such as L2-Net [1] and triplet based metric learning [2].
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Distilling BlackBox to Interpretable models for Efficient Transfer Learning
Building generalizable AI models is one of the primary challenges in the healthcare domain.
Weakly Supervised Disentanglement by Pairwise Similarities
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity.
Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics
(3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN's early layers.
Causal Generative Domain Adaptation Networks
For this purpose, we first propose a flexible Generative Domain Adaptation Network (G-DAN) with specific latent variables to capture changes in the generating process of features across domains.
Transfer Learning with Label Noise
However, when learning this invariant knowledge, existing methods assume that the labels in source domain are uncontaminated, while in reality, we often have access to source data with noisy labels.
Causal Discovery in the Presence of Measurement Error: Identifiability Conditions
This problem has received much attention in multiple fields, but it is not clear to what extent the causal model for the measurement-error-free variables can be identified in the presence of measurement error with unknown variance.
Deep Diffeomorphic Normalizing Flows
We use a neural network to parametrize the smooth vector field and a recursive neural network (RNN) for approximating the solution of the ODE.
An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting: given samples from the mixture and the component distributions, we identify the proportions of the components in the mixture distribution.
Generative-Discriminative Complementary Learning
The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases.
Learning Depth from Monocular Videos Using Synthetic Data: A Temporally-Consistent Domain Adaptation Approach
Due to the stylish difference between synthetic and real images, we propose a temporally-consistent domain adaptation (TCDA) approach that simultaneously explores labels in the synthetic domain and temporal constraints in the videos to improve style transfer and depth prediction.
Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement
Recent work by Locatello et al. (2018) has shown that an inductive bias is required to disentangle factors of interest in Variational Autoencoder (VAE).
Label-Noise Robust Domain Adaptation
Domain adaptation aims to correct the classifiers when faced with distribution shift between source (training) and target (test) domains.
Explaining the Black-box Smoothly- A Counterfactual Approach
We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation.
Using Causal Analysis for Conceptual Deep Learning Explanation
Model explainability is essential for the creation of trustworthy Machine Learning models in healthcare.
Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision
In this paper, we propose a weakly supervised do-main adaptation setting, in which we can partially label newdatasets with bounding boxes, which are easier and cheaperto obtain than segmentation masks.
Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation
An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models.
Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
We use graph neural networks to incorporate the relationship between different anatomical regions.
Hyperbolic Molecular Representation Learning for Drug Repositioning
We use the Variational Auto-Encoder (VAE) framework to encode the chemical structures of molecules and use the drug-drug similarity information obtained from the hierarchy to induce the clustering of drugs in hyperbolic space.
Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier
The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary.
DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images
Extensive experiments on large-scale computer tomography (CT) datasets of lung images show that our method improves the performance of many downstream prediction and segmentation tasks.
From Characters to Words: Hierarchical Pre-trained Language Model for Open-vocabulary Language Understanding
Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens.
Exploring the Lottery Ticket Hypothesis with Explainability Methods: Insights into Sparse Network Performance
The discovered concepts and pixels from the pruned networks are inconsistent with the original network -- a possible reason for the drop in performance.
Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure.
MedSyn: Text-guided Anatomy-aware Synthesis of High-Fidelity 3D CT Images
This study focuses on two main objectives: (1) the development of a method for creating images based on textual prompts and anatomical components, and (2) the capability to generate new images conditioning on anatomical elements.
