nian-liu / Picanet
Stars: ✭ 35
Projects that are alternatives of or similar to Picanet
Raspberrypi Facedetection Mtcnn Caffe With Motion
MTCNN with Motion Detection, on Raspberry Pi with Love
Stars: ✭ 204 (+482.86%)
Mutual labels: jupyter-notebook, caffe, detection
Facemaskdetection
开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask.
Stars: ✭ 1,677 (+4691.43%)
Mutual labels: jupyter-notebook, caffe, detection
Drbox
A deep learning based algorithm to detect rotated object, for example, objects in remote sensing images
Stars: ✭ 379 (+982.86%)
Mutual labels: caffe, detection
Vpgnet
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (ICCV 2017)
Stars: ✭ 382 (+991.43%)
Mutual labels: jupyter-notebook, caffe
Deep Learning Traffic Lights
Code and files of the deep learning model used to win the Nexar Traffic Light Recognition challenge
Stars: ✭ 457 (+1205.71%)
Mutual labels: jupyter-notebook, caffe
Learning
The data is the future of oil, digging the potential value of the data is very meaningful. This library records my road of machine learning study.
Stars: ✭ 330 (+842.86%)
Mutual labels: jupyter-notebook, caffe
Php Opencv Examples
Tutorial for computer vision and machine learning in PHP 7/8 by opencv (installation + examples + documentation)
Stars: ✭ 333 (+851.43%)
Mutual labels: caffe, detection
Android Object Detection
☕️ Fast-RCNN and Scene Recognition using Caffe
Stars: ✭ 295 (+742.86%)
Mutual labels: caffe, detection
Caffenet Benchmark
Evaluation of the CNN design choices performance on ImageNet-2012.
Stars: ✭ 700 (+1900%)
Mutual labels: jupyter-notebook, caffe
Realtime multi Person pose estimation
Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)
Stars: ✭ 4,760 (+13500%)
Mutual labels: jupyter-notebook, caffe
Keras realtime multi Person pose estimation
Keras version of Realtime Multi-Person Pose Estimation project
Stars: ✭ 728 (+1980%)
Mutual labels: jupyter-notebook, caffe
Tensorflow 2.x Yolov3
YOLOv3 implementation in TensorFlow 2.3.1
Stars: ✭ 300 (+757.14%)
Mutual labels: jupyter-notebook, detection
Teacher Student Training
This repository stores the files used for my summer internship's work on "teacher-student learning", an experimental method for training deep neural networks using a trained teacher model.
Stars: ✭ 34 (-2.86%)
Mutual labels: jupyter-notebook, caffe
Cascaded Fcn
Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Stars: ✭ 296 (+745.71%)
Mutual labels: jupyter-notebook, caffe
Deepnetsforeo
Deep networks for Earth Observation
Stars: ✭ 393 (+1022.86%)
Mutual labels: jupyter-notebook, caffe
Fundamentals Of Deep Learning For Computer Vision Nvidia
The repository includes Notebook files and documents of the course I completed in NVIDIA Deep Learning Institute. Feel free to acess and work with the Notebooks and other files.
Stars: ✭ 16 (-54.29%)
Mutual labels: jupyter-notebook, caffe
crowd density segmentation
The code for preparing the training data for crowd counting / segmentation algorithm.
Stars: ✭ 21 (-40%)
Mutual labels: caffe, detection
Sipmask
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
Stars: ✭ 255 (+628.57%)
Mutual labels: jupyter-notebook, detection
PiCANet
source code for our CVPR 2018 paper PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection by Nian Liu, Junwei Han, and Ming-Hsuan Yang.
Created by Nian Liu, Email: [email protected]
Usage:
- Cd to ./caffe, install our modified caffe (given in the source code) and its MATLAB wrapper. Plese refer to http://caffe.berkeleyvision.org/installation.html for caffe installation.
- Download our trained models from Google drive. Unzip them to ./models/models.
- Put your images into ./matlab/images.
- Cd to ./matlab, run 'predict_SOs.m' and the saliency maps will be generated in ./matlab/results. You can also select whether to use the VGG based model or the ResNet50 based model in line 16 or 17.
- You can also consider to use CRF post-processing to improve the detection results like we did in our paper. Please refer to Qibin Hou's code.
- We also provide our saliency maps here.
Training:
- Download the pretrained VGG model (vgg16_20M.caffemodel from deeplab) or the ResNet50 model. Modify the model directories in ./models/train_SO.sh.
- Prepare your images, ground truth saliency maps, and the list file (please refer to ./matlab/list/train_list.txt). Modify corresponding contents in prototxt files.
- Cd to ./models, run
sh train_SO.sh
to start training.
Acknowledgement:
Our code uses some opensource code from deeplab, hybridnet, and a caffe pull request to reduce GPU memory usage. Thank the authors.
Citing our work
Please cite our work if it helps your research:
@inproceedings{liu2018picanet,
title={PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection},
author={Liu, Nian and Han, Junwei and Yang, Ming-Hsuan},
booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={3089--3098},
year={2018}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].