Comments (8)
@DuinoDu
For the first question, we find that not sharing features could get better detection results. Maybe you can have try about sharing weights with four scales.
The objectness prior is modified from RPN. The original RPN will do bbox regression to get better localization, however, the anchor's location will be changed after bbox reg. So Faster R-CNN must use ROI-Pooling to extract features on these changed anchors. Thus the detection module will bring repeated computations.
@mattdingmeng @chengshuai
Yes, the idea of reverse connection is similar with DSSD, FPN and TDM. In fact, the four works are developed amost at the same period. RON and FPN are both accepted by cvpr2017.
from ron.
The reverse connection is similar with the idea of the paper(the Feature Pyramid Networks for Object Detection and Deconvoluiton SSD).
from ron.
@DuinoDu for the second comment, I agree with you. The objectness prior is very close to the rpn in faster rcnn. I think the main contribution of this paper is the reverse connection, which combine different scaled feature map to detect objects in different size.
from ron.
Thanks!
from ron.
I want to know why it is faster than Faster R-CNN.
Who can help me ,thanks a lot
from ron.
@kl456123 the author mentioned it that use ROI-Pooling can bring extra computation. Meanwhile, I think discarding Fully Connection Layer also can accelerate the speed of train and inference.
from ron.
I want to study about the small target detection in large scale scene.
But I find that, the CNN feature Map is very important, If the CNN base model can't find the target, the regression has no meaning.
Could you give me some tips about how to advance the CNN feature model ?
from ron.
by the way, I have sent an email to you to ask some questions about hypernet (https://arxiv.org/abs/1604.00600). Please take a look if you have time:)
from ron.
Related Issues (20)
- Do RON have mxnet version? HOT 3
- Why the trainning is very slow in my dateset HOT 11
- Changing alpha and beta HOT 3
- cuda/cudnn version HOT 1
- BaiduYun HOT 3
- CUDNN error HOT 1
- Multiple objects detection isn't so accurate HOT 5
- No such file or directory: 'data/VOCdevkit2007/results/VOC2007/Main/comp4_det_test_aeroplane.txt'
- Train and Test for input size 384
- demo HOT 1
- set thebatchsize HOT 1
- Why this implementation is different from the paper? HOT 1
- Train RON on KITTI Blocked in pythonlayer::forward
- how to save log HOT 1
- What's the meaning of the number in rpn-data param "param_str" HOT 1
- How can I use RON when the objects of my datasets are all small? HOT 1
- train.prototxt HOT 1
- The demo result is not good HOT 1
- Two questions about the code
- whether to support cpu mode for inference? HOT 2
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 ron.