Piotr Teterwak

I am a second year Ph.D. student at Boston University and am very lucky to be co-advised by Professor Kate Saenko and Professor Bryan Plummer. Prior to my Ph.D., I was an AI Resident on the Perception Team at Google Research, where I spent two amazing years working with Dr. Dilip Krishnan, Dr. Ce Liu, Professor Mike Mozer, and many others. Prior to that, I spent time on the ML team at Apple, and worked at a startup called Turi. I got my Bachelor's degree in Computer Science from Dartmouth College.

Office hours

Insipred by Wei-Chiu Ma (who was in turn inspired by Professors Kyunghyun Cho and Krishna Murthy), I am offering some office hours each week to talk about anything you'd like. I have recently gone through PhD admissions, so have some perspective on that, and am also happy to talk research and graduate student life. Please e-mail me with the subject line "OFFICE HOURS" and give me a brief overview of what you'd like to talk about and what time zone you're in.

Email  /  CV  /  Google Scholar  /  Twitter

profile photo
Research

I'm broadly interested in machine learning and computer vision, and am particularly interested in learning compact but semantically rich representations of our world.

MixtureEnsembles: Leveraging Parameter Sharing for Efficient Ensembles
Piotr Teterwak, Nikoli Dryden, Dina Bashkirova, Kate Saenko Bryan A. Plummer

Preprint coming soon.

Parameter-efficient ensembling.

Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
Kuniaki Saito, Donghyun Kim, Piotr Teterwak, Stan Sclaroff, Trevor Darrell, Kate Saenko

ICCV, 2021

How to determine what hyperparameters to use for unsupervised domain adaptation, without cheating.

VisDA-2021 Competition: Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data
Dina Bashkirova*, Dan Hendrycks*, Donghyun Kim*, Samarth Mishra*, Kate Saenko*, Kuniaki Saito*, Piotr Teterwak* (equal contribution), Ben Usman*

NeurIPS Competition Track, 2021

This challenge tests how well models can (1) adapt to several distribution shifts and (2) detect unknown unknowns.

Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers
Piotr Teterwak, Chiyuan Zhang, Dilip Krishnan, Michael C. Mozer

ICML, 2021

Understanding what information is preserved in classifier logits by training GAN-based inversion model. Surprisingly, we can reconstruct images well, though it depends on architecture and optimization procedure.

OCONet: Image Extrapolation by Object Completion
Richard Strong Bowen, Huiwen Chang, Charles Herrmann, Piotr Teterwak, Ramin Zabih

CVPR, 2021

Improving image extrapolation for objects.

Supervised Contrastive Learning
Prannay Khosla*, Piotr Teterwak* (equal contribution), Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, Dilip Krishnan
NeurIPS, 2020
arXiv

A new loss function to train supervised deep networks, based on contrastive learning. Our new loss performs significantly better than cross-entropy across a range of architectures and data augmentations.

Boundless:Generative Adverserial Networks for Image Extension
Piotr Teterwak, Aaron Sarna, Dilip Krishnan, Aaron Maschinot, David Belanger, Ce Liu, William T. Freeman

ICCV 2019
Project Page
Pretrained Models and Tutorial

We adapt GAN's for the image extrapolation problem, and use a novel feature conditioning to improve results.

Coursework

CS 585 - Image and Video Computing


Template from Jon Barron's really cool website,