Search Results for author: William Lotter

Found 8 papers, 4 papers with code

Representing visual classification as a linear combination of words

1 code implementation18 Nov 2023 Shobhit Agarwal, Yevgeniy R. Semenov, William Lotter

By leveraging a pre-trained joint embedding space between images and text, our approach estimates a new classification task as a linear combination of words, resulting in a weight for each word that indicates its alignment with the vision-based classifier.

Classification Clinical Knowledge +1

Synthesizing lesions using contextual GANs improves breast cancer classification on mammograms

no code implementations MIDL 2019 Eric Wu, Kevin Wu, William Lotter

Breast cancer classification in mammography exemplifies these challenges, with a malignancy rate of around 0. 5% in a screening population, which is compounded by the relatively small size of lesions (~1% of the image) in malignant cases.

Data Augmentation General Classification

Conditional Infilling GANs for Data Augmentation in Mammogram Classification

1 code implementation21 Jul 2018 Eric Wu, Kevin Wu, David Cox, William Lotter

Deep learning approaches to breast cancer detection in mammograms have recently shown promising results.

Breast Cancer Detection Classification +2

A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception

no code implementations28 May 2018 William Lotter, Gabriel Kreiman, David Cox

Interestingly, recent work has shown that deep convolutional neural networks (CNNs) trained on large-scale image recognition tasks can serve as strikingly good models for predicting the responses of neurons in visual cortex to visual stimuli, suggesting that analogies between artificial and biological neural networks may be more than superficial.

Open-Ended Question Answering Predict Future Video Frames

A Multi-Scale CNN and Curriculum Learning Strategy for Mammogram Classification

no code implementations21 Jul 2017 William Lotter, Greg Sorensen, David Cox

Screening mammography is an important front-line tool for the early detection of breast cancer, and some 39 million exams are conducted each year in the United States alone.

General Classification

Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

17 code implementations25 May 2016 William Lotter, Gabriel Kreiman, David Cox

Here, we explore prediction of future frames in a video sequence as an unsupervised learning rule for learning about the structure of the visual world.

Object Recognition Video Prediction

Unsupervised Learning of Visual Structure using Predictive Generative Networks

2 code implementations19 Nov 2015 William Lotter, Gabriel Kreiman, David Cox

The ability to predict future states of the environment is a central pillar of intelligence.

Cannot find the paper you are looking for? You can Submit a new open access paper.