Comments (2)
Hi Lidong, thanks for your interest and your insightful questions!
For question 1, we haven't done any experiment on the comparison. A problem is that the mask used to filter useless information (shaded area) after warping might not be the same with the ground truth occlusion map at each level. Please feel free to draw comparison between our method and others' and we are looking forward to hearing what you discover!
For question 2, we have already released the weights to produce the visualization, so you can use them to produce more! What we think is that, object-object case has smaller size and larger relative motion, so it might be harder than fore-background case, but the mechanisms behind them are the same- background can be seen just as an object with relatively small motion.
from maskflownet.
@simon1727 Thanks for your answer.
For question 1, the reason I talked it is that I used to conduct some exps on occlusion years ago. I did use the occlusion map(ground truth) to guide the refinement, it gave a great promotion. But the promotion becomes not that obvious when I switch the occlusion map to the supervised learned one. Although my result is lost now, I still remember how hard it is to learn the occlusion map.
It is a great discovery of your work to show that the unsupervised learning of attention maps might be more proper to guide the refinement. An unsupervised activation map from the learned feature map in the last few layers indeed shows the attention for the final activation. Thanks again for your discovery.
For question 2, what I am interested in is actually the big motion cases. Object-object cases are always having bigger relative motion. I may be able to generate some cases on crowded scenes if I can access the data later. The problem might be changed if the motion is too big as we all know both Flownet and PWC is hard to cover a low-frequency video. I might need to conduct more exps to see the result.
Thanks again for your great work and patience.
from maskflownet.
Related Issues (20)
- A question on VCN performance in Table 1 HOT 2
- Error in operator maskflownet0_maskflownet_s0_upsample0_reshape_like0 HOT 1
- Details about fine-tune in the Flyingthings3D HOT 3
- Some problems about MXNetError HOT 2
- How to use inference with my own dataset? HOT 5
- TensorFlow or Pytorch port HOT 1
- Can you provide the .state file? HOT 3
- RAM leak problem when training in command batch_queue.get(). Where do you release resources once a batch is trained. HOT 3
- Questions about the provided checkpoints HOT 2
- Mask visualization problem HOT 3
- Typo in network code HOT 1
- Finetuning on chairsSDHom epe doesn't go down. HOT 1
- BGR vs RGB input HOT 1
- What is the variable F in your code please . . . HOT 2
- How to adjust the parameter?
- Question about provided models
- How can I infer my own data by net MaskFlownet_S?
- There is not Network Configuration yaml files
- could not find the yaml file
- Question regarding Occlusion-Aware Pyramid
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 maskflownet.