Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
arXiv:1912.00384
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.
arXiv commentAccepted by Pattern Recognition
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Prototypical Networks for Few-shot Learning
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- CNN: Single-label to Multi-label
- Semi-Supervised Learning with Ladder Networks
- Few-Example Object Detection with Model Communication
- Learning Semantic Part-Based Models from Google Images