# Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos

Source: [Watch and Learn: Semi-Supervised Learning of Object Detectors from Videos](<https://www.sota2.com/research/paper/68fa61e21e209131ce9f65d7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:07:28.348Z

Authors: Ishan Misra, Abhinav Shrivastava, Martial Hebert

Published: 2015-05-21T15:34:30.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1505.05769>)

[PDF](<https://arxiv.org/pdf/1505.05769.pdf>)
