Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

1 code implementation • CVPR 2019 • Hongyang Li, David Eigen, Samuel Dodge, Matthew Zeiler, Xiaogang Wang

Few-shot learning is an important area of research.

Few-Shot Learning Metric Learning

Can the early human visual system compete with Deep Neural Networks?

no code implementations • 12 Oct 2017 • Samuel Dodge, Lina Karam

We study and compare the human visual system and state-of-the-art deep neural networks on classification of distorted images.

General Classification

A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions

no code implementations • 6 May 2017 • Samuel Dodge, Lina Karam

In this work, we compare the performance of DNNs with human subjects on distorted images.

General Classification

Quality Resilient Deep Neural Networks

no code implementations • 23 Mar 2017 • Samuel Dodge, Lina Karam

The "experts" in our model are trained on a particular type of distortion.

Visual Saliency Prediction Using a Mixture of Deep Neural Networks

no code implementations • 1 Feb 2017 • Samuel Dodge, Lina Karam

The final saliency map is computed as a weighted mixture of the expert networks' output, with weights determined by a separate gating network.

Saliency Prediction

Understanding How Image Quality Affects Deep Neural Networks

4 code implementations • 14 Apr 2016 • Samuel Dodge, Lina Karam

We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise.

General Classification Image Classification