Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

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

(1) , (2) , (2) , (1) , (3)
1
2
3

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 are available. In this work, we study the problem of training an object detector from one or few clean 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 classifier or detector. Our solution is to use a standard weakly-supervised pipeline to train a student model from image-level pseudo-labels generated on the unlabeled set by a teacher model, bootstrapped by region-level similarities to clean labeled images. By using the recent pipeline of PCL [47] and more unlabeled images, we achieve performance competitive or superior to many state of the art weakly-supervised detection solutions.
Fichier principal
Vignette du fichier
1912.00384.pdf (2.26 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02393688 , version 1 (04-12-2019)

Identifiers

Cite

Zhaohui Yang, Miaojing Shi, Yannis Avrithis, Chao Xu, Vittorio Ferrari. Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images. 2019. ⟨hal-02393688⟩
52 View
273 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More