Transtreaming: Adaptive Delay-aware Transformer for Real-time Streaming Perception
Abstract
Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception method, Transtreaming, which addresses the challenge of real-time object detection with dynamic computational delay. The core innovation of Transtreaming lies in its adaptive delay-aware transformer, which can concurrently predict multiple future frames and select the output that best matches the real-world present time, compensating for any system-induced computation delays. The proposed model outperforms the existing state-of-the-art methods, even in single-frame detection scenarios, by leveraging a transformer-based methodology. It demonstrates robust performance across a range of devices, from powerful V100 to modest 2080Ti, achieving the highest level of perceptual accuracy on all platforms. Unlike most state-of-the-art methods that struggle to complete computation within a single frame on less powerful devices, Transtreaming meets the stringent real-time processing requirements on all kinds of devices. The experimental results emphasize the system's adaptability and its potential to significantly improve the safety and reliability for many real-world systems, such as autonomous driving.
Cite
@article{arxiv.2409.06584,
title = {Transtreaming: Adaptive Delay-aware Transformer for Real-time Streaming Perception},
author = {Xiang Zhang and Yufei Cui and Chenchen Fu and Weiwei Wu and Zihao Wang and Yuyang Sun and Xue Liu},
journal= {arXiv preprint arXiv:2409.06584},
year = {2024}
}
Comments
Submitted to AAAI 2025