David Eigen
YOU?
Author Swipe
View article: Mutational Signature Refitting on Sparse Pan-Cancer Data
Mutational Signature Refitting on Sparse Pan-Cancer Data Open
Mutational processes shape cancer genomes, leaving characteristic marks that are termed signatures. The level of activity of each such process, or its signature exposure, provides important information on the disease, improving patient str…
View article: Deep learning in medical image analysis: introduction to underlying principles and reviewer guide using diagnostic case studies in paediatrics
Deep learning in medical image analysis: introduction to underlying principles and reviewer guide using diagnostic case studies in paediatrics Open
International audience
View article: Enhancing Worldwide Image Geolocation by Ensembling Satellite-Based Ground-Level Attribute Predictors
Enhancing Worldwide Image Geolocation by Ensembling Satellite-Based Ground-Level Attribute Predictors Open
We examine the challenge of estimating the location of a single ground-level image in the absence of GPS or other location metadata. Currently, geolocation systems are evaluated by measuring the Great Circle Distance between the predicted …
View article: Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images
Development and validation of a smartphone-based deep-learning-enabled system to detect middle-ear conditions in otoscopic images Open
Middle-ear conditions are common causes of primary care visits, hearing impairment, and inappropriate antibiotic use. Deep learning (DL) may assist clinicians in interpreting otoscopic images. This study included patients over 5 years old …
View article: Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space
Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space Open
Recent advances in the field of artificial intelligence have been made possible by deep neural networks. In applications where data are scarce, transfer learning and data augmentation techniques are commonly used to improve the generalizat…
View article: Coarse2Fine: A Two-stage Training Method for Fine-grained Visual\n Classification
Coarse2Fine: A Two-stage Training Method for Fine-grained Visual\n Classification Open
Small inter-class and large intra-class variations are the main challenges in\nfine-grained visual classification. Objects from different classes share\nvisually similar structures and objects in the same class can have different\nposes an…
View article: A Meta-Learning Approach for Custom Model Training
A Meta-Learning Approach for Custom Model Training Open
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples availa…
View article: Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal Open
Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common in practice. Rece…
View article: Gradient Agreement as an Optimization Objective for Meta-Learning
Gradient Agreement as an Optimization Objective for Meta-Learning Open
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are s…
View article: Unsupervised Feature Learning from Temporal Data
Unsupervised Feature Learning from Temporal Data Open
Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled…