On this page, you’ll find links to software, code repositories and datasets that the CLeAR lab has produced.
This repository contains code for the IROS 2020 paper “TactileSGNet: A Spiking Graph Neural Network for Event-based Tactile Object Recognition”. In this paper, we propose a novel spiking graph neural network for event-based tactile object recognition. [Check our Github Page]
This repository contains code for reproducing the experiments presented in the ICLR 2021 paper Refining Deep Generative Models via Discriminator Gradient Flow. In this paper, we propose DGflow, a technique to improve samples from deep generative models using the gradient flow of entropy-regularized f-divergences between the generated and real data distributions. [Check our Github Page]
This repository contains code for the CVPR 2020 paper: A Characteristic Function Approach to Deep Implicit Generative Modeling. In this paper, we propose a method of training a Generative Adversarial Network (GAN) by minimizing the expected distance between empirical characteristic functions of the real and generated data distributions.[Check our Github Page]
This repository contains code for the AAAI 2019 paper: Hyperprior Induced Unsupervised Disentanglement of Latent Representations. In this paper, we show how a simple hierarchical Bayesian VAE leads to controllable latent representations.[Check our Github Page]