Repository files navigation

CVPR18 Paper: Multi-scale Location-aware Kernel Representation for Object Detection. Paper can be found inarXiv andCVPR2018.

MLKP is a novel compact, location-aware kernel approximation method to represent object proposals for effective object detection. Our method is among the first which exploits high-order statistics in improving performance of object detection. The significant improvement over the first-order statistics based counterparts demonstrates the effectiveness of the proposed MLKP.

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

@InProceedings{Wang_2018_CVPR,author = {Wang, Hao and Wang, Qilong and Gao, Mingqi and Li, Peihua and Zuo, Wangmeng},title = {Multi-Scale Location-Aware Kernel Representation for Object Detection},booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},month = {June},year = {2018}}

@article{wang2021multi,  title={Multi-scale structural kernel representation for object detection},  author={Wang, Hao and Wang, Qilong and Li, Peihua and Zuo, Wangmeng},  journal={Pattern Recognition},  volume={110},  pages={107593},  year={2021},  publisher={Elsevier}}

The code is modified frompy-faster-rcnn.

For multi-gpu training, please refer topy-R-FCN-multiGPU

• OS: Linux 14.02
• GPU: TiTan 1080 Ti
• CUDA: version 8.0
• CUDNN: version 5.0

Slight changes may not results instabilities

We have re-trained our networks and the results are refreshed as belows:

Results can be found atVGG16 andResNet

0. Clone the MLKP repository

   git clone https://github.com/Hwang64/MLKP.git

1. Build Caffe and pycaffe

   cd $MLKP_ROOTgit clone https://github.com/Hwang64/caffe-mlkp.gitcd caffe-mlkpmake cleanmake all -j16 && make pycaffe

2. Build the Cython modules

   cd $MLKP_ROOT/libmake

3. installation for training and testing models on PASCAL VOC dataset

   3.0 The PASCAL VOC dataset has the basic structure:

    $VOCdevkit/                           # development kit $VOCdevkit/VOCcode/                   # VOC utility code $VOCdevkit/VOC2007                    # image sets, annotations, etc.

   3.1 Create symlinks for the PASCAL VOC dataset

    cd $MLKP_ROOT/data ln -s $VOCdevkit VOCdevkit2007 ln -s $VOCdevkit VOCdevkit2012

   For more details, please refer topy-faster-rcnn.

4. Test with PASCAL VOC dataset

   We provide PASCAL VOC 2007 pretrained models based on VGG16 and ResNet, please download the models manully fromBaiduYun orGoogleDrive and put them in$MLKP_ROOT/output/

   4.0 Test VOC07 using VGG16 network

   python ./tools/test_net.py --gpu 0\         --def models/VGG16/test.prototxt\         --net output/VGG16_voc07_test.caffemodel\         --imdb voc_2007_test\         --cfg experiments/cfgs/faster_rcnn_end2end.yml

   The final results of the model is mAP=78.4%

   4.1 Test VOC07 using ResNet-101 network

   python ./tools/test_net.py --gpu 0\          --def models/ResNet/test.prototxt\          --net output/ResNet_voc07_test.caffemodel\          --imdb voc_2007_test\          --cfg experiments/cfgs/faster_rcnn_end2end.yml

   The final results of the model is mAP=81.0%

5. Train with PASCAL VOC dataset

   Please download ImageNet-pretrained models first and put them into$data/ImageNet_models.

   5.0 Train using single GPU

   python ./tools/train_net.py --gpu 0\         --solver models/VGG16/solver.prototxt\        --weights data/ImageNet_models/VGG16.v2.caffemodel\        --imdb voc_2007_trainval+voc_2012_trainval\         --cfg experiments/cfgs/faster_rcnn_end2end.yml

   5.1 Train using multi-GPUs

   python ./tools/train_net_multi_gpu.py --gpu 0,1,2,3\        --solver models/VGG16/solver.prototxt\        --weights data/ImageNet_models/VGG16.v2.caffemodel\        --imdb voc_2007_trainval+voc_2012_trainval\        --cfg experiments/cfgs/faster_rcnn_end2end.yml