Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos
This work addresses the challenge of semi-supervised object detection in videos for computer vision applications, offering a more generic approach compared to existing methods that rely on motion or handle fewer instances.
The paper tackles the problem of localizing multiple unknown object instances in long videos with minimal labeled data, achieving results by iteratively learning and labeling hundreds of thousands of instances using criteria for reliable detection and tracking to minimize semantic drift.
We present a semi-supervised approach that localizes multiple unknown object instances in long videos. We start with a handful of labeled boxes and iteratively learn and label hundreds of thousands of object instances. We propose criteria for reliable object detection and tracking for constraining the semi-supervised learning process and minimizing semantic drift. Our approach does not assume exhaustive labeling of each object instance in any single frame, or any explicit annotation of negative data. Working in such a generic setting allow us to tackle multiple object instances in video, many of which are static. In contrast, existing approaches either do not consider multiple object instances per video, or rely heavily on the motion of the objects present. The experiments demonstrate the effectiveness of our approach by evaluating the automatically labeled data on a variety of metrics like quality, coverage (recall), diversity, and relevance to training an object detector.