CorrDiff: Adaptive Delay-aware Detector with Temporal Cue Inputs for Real-time Object Detection
Xiang Zhang, Chenchen Fu, Yufei Cui, Lan Yi, Yuyang Sun, Weiwei Wu,, Xue Liu

TL;DR
CorrDiff is a real-time object detection method that adaptively compensates for delays using temporal cues, improving accuracy and robustness across various devices for autonomous driving applications.
Contribution
It introduces an adaptive delay-aware detector that predicts future object locations using runtime-estimated temporal cues, enhancing real-time detection performance.
Findings
Outperforms state-of-the-art methods in mAP and sAP metrics.
Achieves real-time processing on diverse hardware platforms.
Demonstrates robustness and improved safety in autonomous driving scenarios.
Abstract
Real-time object detection takes an essential part in the decision-making process of numerous real-world applications, including collision avoidance and path planning in autonomous driving systems. This paper presents a novel real-time streaming perception method named CorrDiff, designed to tackle the challenge of delays in real-time detection systems. The main contribution of CorrDiff lies in its adaptive delay-aware detector, which is able to utilize runtime-estimated temporal cues to predict objects' locations for multiple future frames, and selectively produce predictions that matches real-world time, effectively compensating for any communication and computational delays. The proposed model outperforms current state-of-the-art methods by leveraging motion estimation and feature enhancement, both for 1) single-frame detection for the current frame or the next frame, in terms of the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCCD and CMOS Imaging Sensors
