segDeepM

Paper

Yukun Zhu, Raquel Urtasun, Ruslan Salakhutdinov and Sanja Fidler, segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection, In Computer Vision and Pattern Recognition (CVPR), Boston, 2015. [arXiv] [leaderboard]

@inproceedings{ZhuSegDeepM15,
title = {segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection},
author = {Yukun Zhu and Raquel Urtasun and Ruslan Salakhutdinov and Sanja Fidler},
booktitle = {CVPR},
year = {2015}
}

Code

[GitHub]

Data

CPMC segments (4.43GB)

o2p potentials for PASCAL VOC 2010 train-val.(226MB)

o2p potentials for PASCAL VOC 2010 trainval-test.(444MB)

Trained Models

Fine-tuned VGG network for PASCAL VOC 2010 dataset [appearnce cnn][context cnn]

Detections (coming soon)

Detection results on PASCAL VOC 2010 val (trained on train)

Detection results on PASCAL VOC 2010 test (trained on train+val)