Identity-Consistent Aggregation for Video Object Detection

TL;DR

This paper introduces ClipVID with Identity-Consistent Aggregation layers that enhance video object detection by focusing on consistent object identities across frames, achieving state-of-the-art accuracy and significantly faster processing speeds.

Contribution

The paper proposes an efficient VID model with identity-consistent aggregation that improves object representation and detection accuracy while enabling parallel clip-wise predictions.

Findings

Achieves 84.7% mAP on ImageNet VID dataset.

Runs at 39.3 fps, 7 times faster than previous methods.

Outperforms state-of-the-art in both accuracy and speed.

Abstract

In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects indiscriminately and ignore their different identities. While intuitively, aggregating local views of the same object in different frames may facilitate a better understanding of the object. Thus, in this paper, we aim to enable the model to focus on the identity-consistent temporal contexts of each object to obtain more comprehensive object representations and handle the rapid object appearance variations such as occlusion, motion blur, etc. However, realizing this goal on top of existing VID models faces low-efficiency problems due to their redundant region proposals and nonparallel frame-wise prediction manner. To aid this, we propose ClipVID, a VID model equipped with Identity-Consistent Aggregation (ICA) layers specifically designed for mining fine-grained and identity-consistent temporal contexts. It effectively reduces the redundancies through the set prediction strategy, making the ICA layers very efficient and further allowing us to design an architecture that makes parallel clip-wise predictions for the whole video clip. Extensive experimental results demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7x faster (39.3 fps) than previous SOTAs.