Skip to main content
← Back to seminars

Past talk · AI/ML Seminar Series

Instance-adaptive data compression: Improving Neural Codecs by Training on the Test Set

Ties van Rozendaal

Senior Machine Learning Researcher, Qualcomm AI Research

Date & time
Monday, May 9, 2022 · 1:00 PM
Location
Donald Bren Hall 4011

Abstract

Neural data compression has been shown to outperform classical methods in terms of rate-distortion performance. These models are fitted to a training dataset and cannot be expected to optimally compress test data in general, due to limits on model capacity, distribution shifts, and imperfect optimization. Instance-adaptive methods take adaptation to the extreme, adapting the model to a single test instance and signaling the updated model in the bitstream. In this talk, we show the potential of different types of instance-adaptive methods and discuss the tradeoffs they pose.

About the speaker

Ties van Rozendaal is a senior machine learning researcher at Qualcomm AI Research. He obtained his master's degree at the University of Amsterdam and works on neural compression, with a focus on using generative models to compress image and video data, including semantic, instance-adaptive, and neural-implicit compression.