Comments (3)
Thanks for your interest.
There are two ways to verify information leakage or not.
- Please check the reconstruction loss. It can empirically prove there is no information leakage happen inside ConvMAE.
https://drive.google.com/file/d/1Je9ClIGCQP43xC3YURVFPnaMRC0-ax1h/view?usp=sharing - Inside stage 1 and stage 2, spatial information aggregation happen at depthwise convolution operation. Masking on DW can prevent information leakage. Adding mask operations on other operator is redundant.
from convmae.
Hi @gaopengpjlab and @Alpha-VL ,
I just find out this thread discussing the issue I was curious to know. I can understand that the local attention only works on dw-conv but there is still an FFN after it. It is possible that FFN mixes some information from the skip connection branch and leads to the leakage. For the extreme case, the possibility of network learning to pass the original image throughout the all model by skip connection is still held. Let me know if I misunderstand anything. Thanks!
from convmae.
Yeach, I have the same doubt.
from convmae.
Related Issues (20)
- Question about VideoConvMAE HOT 3
- Running pretrained convvit on larger image sizes HOT 1
- Question about ConvMAE-v2 HOT 4
- Hi HOT 1
- Train on HOT 2
- Doubts about masking strategy
- Total memory consumption for training with 32 batch size. HOT 6
- How long will the the pretraining stage takes in V100?
- refactor hard coded numbers for more control over parameters (MaskedAutoencoderConvViT) HOT 1
- How can i train 200 epoches for DET ? HOT 15
- why still can't find the paper or details of ConvMAE-v2? HOT 2
- image unpatchify related problems HOT 2
- hi,i need help HOT 1
- full checkpoint
- Questions about convmae-v2
- Model Settings and checkpoint not match
- about the training loss HOT 1
- Visualization VIT feature
- When will you update the MR-MCMAE model?
- Why not use the masked transformers directly in the first two stages?
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 convmae.