# Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images

Source: [Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images](<https://www.sota2.com/research/paper/68fa6a5e1e209131cea27c02>)

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

Data updated: 2026-01-04T03:15:00.510Z

Authors: Zhaohui Yang, Miaojing Shi, Chao Xu, Vittorio Ferrari, Yannis Avrithis

Published: 2019-12-01T11:09:48.000Z

## Abstract

Weakly-supervised object detection attempts to limit the amount of supervision by dispensing the need for bounding boxes, but still assumes image-level labels on the entire training set. In this work, we study the problem of training an object detector from one or few images with image-level labels and a larger set of completely unlabeled images. This is an extreme case of semi-supervised learning where the labeled data are not enough to bootstrap the learning of a detector. Our solution is to train a weakly-supervised student detector model from image-level pseudo-labels generated on the unlabeled set by a teacher classifier model, bootstrapped by region-level similarities to labeled images. Building upon the recent representative weakly-supervised pipeline PCL, our method can use more unlabeled images to achieve performance competitive or superior to many recent weakly-supervised detection solutions.

## 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.

- [Object Detection on PASCAL VOC 2012 (test)](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-2012-test.md>): Object Detection; PASCAL VOC 2012 (test); mAP: 38.6.

- [Object Detection on PASCAL VOC 2007 (test)](<https://www.sota2.com/research/sota/object-detection-on-pascal-voc-2007-test.md>): Object Detection; PASCAL VOC 2007 (test); mAP: 42.

- [Object Localization on PASCAL VOC 2007 (trainval)](<https://www.sota2.com/research/sota/object-localization-on-pascal-voc-2007-trainval.md>): Object Localization; PASCAL VOC 2007 (trainval); CorLoc: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.00384>)

[PDF](<https://arxiv.org/pdf/1912.00384.pdf>)

[Implementation](<https://github.com/zhaohui-yang/NSOD>)
