# Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training

Source: [Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training](<https://www.sota2.com/research/paper/69a1251d2d603e6de3e3c676>)

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

Data updated: 2026-07-22T05:00:05.107Z

Authors: Aheli Saha, Ren\\'e Schuster, Didier Stricker

Published: 2026-02-26T18:57:52.000Z

## Abstract

Bio-inspired event cameras have recently attracted significant research due to their asynchronous and low-latency capabilities. These features provide a high dynamic range and significantly reduce motion blur. However, because of the novelty in the nature of their output signals, there is a gap in the variability of available data and a lack of extensive analysis of the parameters characterizing their signals. This paper addresses these issues by providing readers with an in-depth understanding of how intrinsic parameters affect the performance of a model trained on event data, specifically for object detection. We also use our findings to expand the capabilities of the downstream model towards sensor-agnostic robustness.

## 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/2602.23357>)

[PDF](<https://arxiv.org/pdf/2602.23357.pdf>)