Search Results for author:
Found 21 papers, 5 papers with code
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
A recent trend is to adapt FID to medical imaging through feature extractors trained on medical images.
Ranked #1 on
Medical Image Generation
on SLIVER07
Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation
Clinically deployed segmentation models are known to fail on data outside of their training distribution.
A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks
A key property of neural networks (both biological and artificial) is how they learn to represent and manipulate input information in order to solve a task.
StyleGAN2-based Out-of-Distribution Detection for Medical Imaging
Our OOD test data consisted of CT images of the brain, head and neck, lung, cervix, and abnormal livers.
Linking convolutional kernel size to generalization bias in face analysis CNNs
Our framework is experimental, in that we train several versions of a network with an intervention to a specific hyperparameter, and measure the resulting causal effect of this choice on performance bias when a particular out-of-distribution image perturbation is applied.
Evaluating the Performance of StyleGAN2-ADA on Medical Images
Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images.
Ranked #1 on
Medical Image Generation
on ACDC
Dyadic Interaction Assessment from Free-living Audio for Depression Severity Assessment
Psychomotor retardation in depression has been associated with speech timing changes from dyadic clinical interviews.
Understanding robustness and generalization of artificial neural networks through Fourier masks
Our results also indicate that the essential frequencies in question are effectively the ones used to achieve generalization in the first place.
Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
Inspired by the original one hundred BPs, we propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning.
An Improved Semi-Supervised VAE for Learning Disentangled Representations
Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning.
Semi-Supervised StyleGAN for Disentanglement Learning
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation.
Adversarial Attacks on Machine Learning Systems for High-Frequency Trading
Algorithmic trading systems are often completely automated, and deep learning is increasingly receiving attention in this domain.
DeepSimplex: Reinforcement Learning of Pivot Rules Improves the Efficiency of Simplex Algorithm in Solving Linear Programming Problems
We use deep value-based reinforcement learning to learn a pivoting strategy that at each iteration chooses between two of the most popular pivot rules -- Dantzig and steepest edge.
Disentangled GANs for Controllable Generation of High-Resolution Images
Generative adversarial networks (GANs) have achieved great success at generating realistic samples.
Neural Rendering Model: Joint Generation and Prediction for Semi-Supervised Learning
The conjugate prior yields a new regularizer for learning based on the paths rendered in the generative model for training CNNs–the Rendering Path Normalization (RPN).
Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs
We study the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.
A Probabilistic Framework for Deep Learning
We develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables.
Semi-Supervised Learning with the Deep Rendering Mixture Model
Semi-supervised learning algorithms reduce the high cost of acquiring labeled training data by using both labeled and unlabeled data during learning.
A Deep Learning Approach to Structured Signal Recovery
In this paper, we develop a new framework for sensing and recovering structured signals.
A Probabilistic Theory of Deep Learning
A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation.
