Skip to content
Few-Example Object Detection with Model Communication, T-PAMI 2018
Branch: master
Clone or download
Latest commit 833e4b5 Aug 3, 2018
Type Name Latest commit message Commit time
Failed to load latest commit information.
datasets update the few-example object detection Feb 3, 2018
external ADD the dataset README Aug 3, 2018
fetch_data Update download link and auto-download scripts Aug 31, 2016
functions update README Jul 12, 2018
imdb update the few-example object detection Feb 3, 2018
models update the few-example object detection Feb 3, 2018
.gitignore add LICENSE Jul 12, 2018 add LICENSE Jul 12, 2018
mspld_build.m update the few-example object detection Feb 3, 2018
ss_build.m add selective search and optimize training codes Mar 11, 2017
startup.m update the few-example object detection Feb 3, 2018

Few-Example Object Detection with Model Communication

By Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng


This project aims to solve the few-example object detection problem, in which there are only a few images with bounding box annotations per object class and a large number of images without annotations. We propose an algorithm to combine the self-paced learning and the multi-modal learning, and we call it Multi-modal Self-Paced Learning for Detection (MSPLD). The implementation is modified from R-FCN and Faster RCNN.

Note that few-example object detection is a special case of semi-supervised object detection. However, most works on semi-supervised object detection assume that some classes have many strong bounding boxes, while others have weak image-level labels. A brief comparison between MSPLD and weakly supervised/semi-supervised/few-example object detection is shown below:

Please refer to the paper for more detailed comparison.


If you find MSPLD useful in your research, please consider citing:

  title   = {Few-Example Object Detection with Model Communication},
  author  = {Dong, Xuanyi and Zheng, Liang and Ma, Fan and Yang, Yi and Meng, Deyu},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
  doi     = {10.1109/TPAMI.2018.2844853}, 
  ISSN    = {0162-8828}, 
  year    = {2018}


Requirements: software

  • Caffe build for MSPLD (included in this repository, see external/caffe)
  • MATLAB 2014a or later

Data Preparation

  • Download PASCAL VOC 2007 and PASCAL VOC 2012. Follow the README in datasets
  • Download the region proposals extracted by Selective Search or EdgeBox.
  • Download the pre-trained Imagenet models for ResNet, VGG, and GoogleNet

Training & Testing

  1. Run experiments/VOC07_Tr_Res50E_Res101S_VGG16F to repoduce the results on VOC 2007.


  1. Selective Search Data: Google Drive
  2. YFCC100M Data for Ablative Study: Google Drive
  3. Detection models are in the models directory.
You can’t perform that action at this time.