Modular Object-Oriented Games (MOOG): Python-based game engine for reinforcement learning, psychology, and neurophysiology.

A framework for analyzing computer vision models with simulated data

Neural Factorization of Shape and Reflectance Under an Unknown Illumination

Implementation of the CVPR 2019 Paper - Speech2Face: Learning the Face Behind a Voice by MIT CSAIL

PyTorch implementations for both unpaired and paired image-to-image translation.

Language learners often use subtitled videos to help them learn. However, standard subtitles are geared more towards comprehension than vocabulary learning, as translations are nonliteral and are provided only for phrases, not vocabulary. This paper presents Smart Subtitles, which are interactive subtitles tailored towards vocabulary learning. 

MiniPlaces Challenge: an Educational Tool for Deep Learning in Computer Vision

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard benchmarks in meta-learning. In this work, we show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, followed by training a linear classifier on top of this representation, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation.

This repository contains the demo code for the CVPR'17 paper Network Dissection: Quantifying Interpretability of Deep Visual Representations. You can use this code with naive Caffe, with matcaffe and pycaffe compiled. We also provide a PyTorch wrapper to apply NetDissect to probe networks in PyTorch format.

GAN Dissection is a way to inspect the internal representations of a generative adversarial network (GAN) to understand how internal units align with human-interpretable concepts. It is part of NetDissect.