Comments (2)
@inlmouse Thanks for your interest in our work. As we know, Cascade CNN in CVPR 2015 is the first work that uses three stages of CNNs to detect faces. Both MT-CNN and our PCN are based on the work of Cascade CNN, while these two works aim to solve different problems in face detection, leading to similar but clearly distinct architectures. The motivation of MT-CNN is to take advantages of multiple relevant tasks to improve accuracy on generic face detection, and thus it simply adds to each CNN two branches for bounding box and landmark prediction. By contrast, our PCN focuses on robustly detecting faces within full range of 360 degrees of in-plane rotation, leading to the design of progressively calibrating rotated faces stage by stage to efficiently handle large appearance variations of them. The calibration tasks of different CNNs in our PCN are logically connected, which is more than combining multiple tasks. Besides, the idea in MT-CNN and PCN are compatible, and can benefit from each other.
Indeed, MT-CNN is a good work on face detection and we have cited MT-CNN in our paper (Reference [23]). We do not provide independent discussions on MT-CNN, since it addresses a different problem and there are other works more relevant to ours, i.e. aiming to solve rotation-variant face detection, which are extensively discussed and compared in our paper.
The highlight of our PCN is the progressive calibration mechanism that can improve the accuracy of rotation-invariant face detection obviously with little time cost. According to our experimental results, advanced detectors using much larger networks, e.g. Faster R-CNN/R-FCN/SSD using VGG-16/ResNet-50, lags behind our PCN in terms of recall when producing a reasonable number of false positives. And the baseline Cascade CNN is significantly outperformed by our PCN. If you can provide quantitative experimental results of directly training MT-CNN on rotated faces, we will be very glad for further discussions.
from facekit.
Has some different with MTCNN.
In all,great works!
from facekit.
Related Issues (20)
- Has anyone implemented training PCN from scratch?
- Run PyPCN on debian11 HOT 1
- What does angle range mean? I use the default code, but it performs bad on down faces, but when I change it to 90, it performs better.
- Discrete ROC Curves
- Stage 1: Calculate rx, ry HOT 1
- what the method of tracking?
- Alignment Output Failure HOT 1
- 请问有没有将PCN与基于landmark的角度估计进行对比?
- face tracker with unique id
- 如何用自己的数据训练 HOT 2
- error LNK2005
- How to convert the square results to rectangles?
- can we run this on raspberry pi
- 你好,是否有开源PCN训练代码的计划呢? HOT 1
- 大家用PCN有没有遇到内存泄漏的问题 HOT 3
- 关于训练数据的问题 HOT 6
- 能给我提供一些关于第三阶段网络训练数据的建议吗,卡在这了,分类和角度准确率都很高了仍然还会出现很多误检 HOT 1
- : cannot connect to X server while running PyPCN.py
- 论文“Samples whose RIP angles are not in the range above will not contribute to the training of calibration.”
- BUG: Static variables in "PCN. CPP" cause an bug
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from facekit.