Learning Probabilistic Models from Generator Latent Spaces with Hat EBM

1 code implementation • 29 Oct 2022 • Mitch Hill, Erik Nijkamp, Jonathan Mitchell, Bo Pang, Song-Chun Zhu

This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM).

EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling

1 code implementation • 24 May 2022 • Mitch Hill, Jonathan Mitchell, Chu Chen, Yuan Du, Mubarak Shah, Song-Chun Zhu

This work presents strategies to learn an Energy-Based Model (EBM) according to the desired length of its MCMC sampling trajectories.

Adversarial Defense Image Generation +1

Stochastic Security: Adversarial Defense Using Long-Run Dynamics of Energy-Based Models

1 code implementation • ICLR 2021 • Mitch Hill, Jonathan Mitchell, Song-Chun Zhu

Our contributions are 1) an improved method for training EBM's with realistic long-run MCMC samples, 2) an Expectation-Over-Transformation (EOT) defense that resolves theoretical ambiguities for stochastic defenses and from which the EOT attack naturally follows, and 3) state-of-the-art adversarial defense for naturally-trained classifiers and competitive defense compared to adversarially-trained classifiers on Cifar-10, SVHN, and Cifar-100.

Adversarial Defense Robust classification

Bounding Box Embedding for Single Shot Person Instance Segmentation

no code implementations • 20 Jul 2018 • Jacob Richeimer, Jonathan Mitchell

We present a bottom-up approach for the task of object instance segmentation using a single-shot model.

Instance Segmentation Object +2