Comments (3)
from dis.
@xuebinqin Thank you for your reply.
Thanks for your interest. There are multiple different skip connections. Even the shallowest skip connections are after at least one convolution layer, which is trying to pass the details to the high-dimensional space. So your comments "the GT encoder can pass all the information from the input to the output without compressing or processing any high-level info since there are skip connections” is not very accurate, since the GT encoder is also deeply supervised and we cannot ignore these layers at the bottom.
I think there is still a possibility (not really) that it can pass the input directly to the output without processing even though there are convolution layers or kernels. One kernel might be just like the below and pass all the information:
However, now I see your point. We can't ignore other layers and the random initialization of the kernel values which means such a case will never happen, right? So, with the convolution layer at the beginning, the input mask will be distorted a bit no matter what we do or how we initialize the model. Also, the other layers will play a role in distorting the input or some of them in fixing the distortion. Then, the distorted input will be translated to the original input all the way, which the last layer will take different parts of information from different kernel results of the previous conv layer. We take feature maps before the last conv which gives us richer information about the input map. I am just trying to enrich my understanding. Your comments about this are really important to me.
More importantly, the features produced by the GT encoder used for supervising the training of DIS have more channels than the single-channel ground truth. So the gt encoder can be understood like a ground truth decompositor or descriptor other than a compressor. The GT encoder tries to convert the ground truth to another high-dimensional space, which provides supervisions from different perspectives. The motivation is to provide denser supervision for the training process for reducing the overfitting. Of course, there must be other better ways to encode the ground truth. We believe there are more possibilities that need to be explored. In this paper, we just provide one possible way to do that. You can also try to remove the skip connections and to see if that works better, which would be a very interesting topic.
Now, I look at the GT encoder from a different perspective. I get it that it is like a decomposer providing more meaningful features about the mask. Thank you again @xuebinqin ! I have been following your research for a while and I am happy about it. Hope you will develop more amazing ideas!
from dis.
Closing the issue.
from dis.
Related Issues (20)
- May I ask how to install the DIS environment on Windows
- 运行train_valid_inference_main.py文件时爆显存
- My GPU is barely under load, but my CPU is at 50% while training HOT 1
- unable to download DIS5K Dataset
- error HOT 1
- Logic behind F1-Score calculation
- DIS V2 HOT 1
- An error occurred when running Python train_valid_reference_main.py HOT 2
- the model starts to remove the object also when fine tuning on the isnet.pth weights HOT 2
- Made my Mac Go Blank Screen
- Need Suggestion for Result on High Resolution Images HOT 5
- Dataset for Segmenting Humans HOT 2
- How to train with multiple GPUs on one machine
- Install the pip package to use the dis-b
- There will always be a translucent background, I don't know what's causing it
- Low quality model on High resolution Images
- -Closed-
- Bad performance on low contrast images
- Error to load the encoder weights
- Suggestion to train gt_encoder or not
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 dis.