# Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning

Source: [Unsupervised Domain Adaptation for Training Event-Based Networks Using Contrastive Learning and Uncorrelated Conditioning](<https://www.sota2.com/research/paper/68fa6ecd1e209131cea423dd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:06:49.536Z

Authors: Dayuan Jian, Mohammad Rostami

Published: 2023-03-22T09:51:08.000Z

## Abstract

Event-based cameras offer reliable measurements for preforming computer vision tasks in high-dynamic range environments and during fast motion maneuvers. However, adopting deep learning in event-based vision faces the challenge of annotated data scarcity due to recency of event cameras. Transferring the knowledge that can be obtained from conventional camera annotated data offers a practical solution to this challenge. We develop an unsupervised domain adaptation algorithm for training a deep network for event-based data image classification using contrastive learning and uncorrelated conditioning of data. Our solution outperforms the existing algorithms for this purpose.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.12424>)

[PDF](<https://arxiv.org/pdf/2303.12424.pdf>)