Receptive Field Block Net for Accurate and Fast Object Detection
By Songtao Liu, Di Huang, Yunhong Wang
here!, stronger YOLO with ONNX, TensorRT, ncnn, and OpenVino supported!!
Updatas (2021/07/23): YOLOX ishere
Updates: we propose a new method to get 42.4 mAP at 45 FPS on COCO, code is availableIntroduction
Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the discriminability and robustness of features. We further assemble the RFB module to the top of SSD with a lightweight CNN model, constructing the RFB Net detector. You can use the code to train/evaluate the RFB Net for object detection. For more details, please refer to our ECCV paper.
VOC2007 Test
System | mAP | FPS (Titan X Maxwell) |
---|---|---|
Faster R-CNN (VGG16) | 73.2 | 7 |
YOLOv2 (Darknet-19) | 78.6 | 40 |
R-FCN (ResNet-101) | 80.5 | 9 |
SSD300* (VGG16) | 77.2 | 46 |
SSD512* (VGG16) | 79.8 | 19 |
RFBNet300 (VGG16) | 80.7 | 83 |
RFBNet512 (VGG16) | 82.2 | 38 |
COCO
System | test-dev mAP | Time (Titan X Maxwell) |
---|---|---|
Faster R-CNN++ (ResNet-101) | 34.9 | 3.36s |
YOLOv2 (Darknet-19) | 21.6 | 25ms |
SSD300* (VGG16) | 25.1 | 22ms |
SSD512* (VGG16) | 28.8 | 53ms |
RetinaNet500 (ResNet-101-FPN) | 34.4 | 90ms |
RFBNet300 (VGG16) | 30.3 | 15ms |
RFBNet512 (VGG16) | 33.8 | 30ms |
RFBNet512-E (VGG16) | 34.4 | 33ms |
MobileNet
System | COCO minival mAP | #parameters |
---|---|---|
SSD MobileNet | 19.3 | 6.8M |
RFB MobileNet | 20.7 | 7.4M |
Citing RFB Net
Please cite our paper in your publications if it helps your research:
@InProceedings{Liu_2018_ECCV,
author = {Liu, Songtao and Huang, Di and Wang, andYunhong},
title = {Receptive Field Block Net for Accurate and Fast Object Detection},
booktitle = {The European Conference on Computer Vision (ECCV)},
month = {September},
year = {2018}
}
Contents
Installation
- Install PyTorch-0.4.0 by selecting your environment on the website and running the appropriate command.
- Clone this repository. This repository is mainly based on ssd.pytorch and Chainer-ssd, a huge thank to them.
- Note: We currently only support PyTorch-0.4.0 and Python 3+.
- Compile the nms and coco tools:
./make.sh
Note: Check you GPU architecture support in utils/build.py, line 131. Default is:
'nvcc': ['-arch=sm_52',
- Then download the dataset by following the instructions below and install opencv.
conda install opencv
Note: For training, we currently support VOC and COCO.
Datasets
To make things easy, we provide simple VOC and COCO dataset loader that inherits torch.utils.data.Dataset
making it fully compatible with the torchvision.datasets
API.
VOC Dataset
Download VOC2007 trainval & test
<div class="highlight highlight-source-shell position-relative overflow-auto" data-snippet-clipboard-copy-content="# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2007.sh # “>
# specify a directory for dataset to be downloaded into, else default is ~/data/ sh data/scripts/VOC2007.sh # <directory>