DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving

TL;DR

DAMO-StreamNet is a novel framework for real-time streaming perception in autonomous driving, combining advanced neural modules and distillation techniques to outperform existing methods in accuracy and efficiency.

Contribution

Introduces DAMO-StreamNet, a new streaming perception framework with innovative modules like deformable convolution and dual-branch structure, setting new benchmarks without extra data.

Findings

Achieves 37.8% sAP on normal size input

Achieves 43.3% sAP on large size input

Outperforms current state-of-the-art methods

Abstract

Real-time perception, or streaming perception, is a crucial aspect of autonomous driving that has yet to be thoroughly explored in existing research. To address this gap, we present DAMO-StreamNet, an optimized framework that combines recent advances from the YOLO series with a comprehensive analysis of spatial and temporal perception mechanisms, delivering a cutting-edge solution. The key innovations of DAMO-StreamNet are (1) A robust neck structure incorporating deformable convolution, enhancing the receptive field and feature alignment capabilities (2) A dual-branch structure that integrates short-path semantic features and long-path temporal features, improving motion state prediction accuracy. (3) Logits-level distillation for efficient optimization, aligning the logits of teacher and student networks in semantic space. (4) A real-time forecasting mechanism that updates support frame features with the current frame, ensuring seamless streaming perception during inference. Our experiments demonstrate that DAMO-StreamNet surpasses existing state-of-the-art methods, achieving 37.8% (normal size (600, 960)) and 43.3% (large size (1200, 1920)) sAP without using extra data. This work not only sets a new benchmark for real-time perception but also provides valuable insights for future research. Additionally, DAMO-StreamNet can be applied to various autonomous systems, such as drones and robots, paving the way for real-time perception. The code is at https://github.com/zhiqic/DAMO-StreamNet.