Label-Efficient Online Continual Object Detection in Streaming Video

TL;DR

This paper introduces LEOCOD, a new approach for online continual object detection in streaming videos that reduces annotation costs while maintaining high performance, outperforming fully supervised methods with significantly fewer labels.

Contribution

The authors propose Efficient-CLS, a plug-and-play module that enhances existing continual learners for video object detection with minimal supervision, reducing annotation effort and retraining time.

Findings

Achieves significant performance improvements with minimal forgetting across supervision levels.

With only 25% annotated frames, outperforms fully supervised models trained on all frames.

Demonstrates effectiveness on challenging real-world video benchmarks.

Abstract

Humans can watch a continuous video stream and effortlessly perform continual acquisition and transfer of new knowledge with minimal supervision yet retaining previously learnt experiences. In contrast, existing continual learning (CL) methods require fully annotated labels to effectively learn from individual frames in a video stream. Here, we examine a more realistic and challenging problem$\unicode{x2014}$Label-Efficient Online Continual Object Detection (LEOCOD) in streaming video. We propose a plug-and-play module, Efficient-CLS, that can be easily inserted into and improve existing continual learners for object detection in video streams with reduced data annotation costs and model retraining time. We show that our method has achieved significant improvement with minimal forgetting across all supervision levels on two challenging CL benchmarks for streaming real-world videos. Remarkably, with only 25% annotated video frames, our method still outperforms the base CL learners, which are trained with 100% annotations on all video frames. The data and source code will be publicly available at https://github.com/showlab/Efficient-CLS.