Comments (3)
z-x-yang
commented on July 23, 2024
No. The key_padding_mask is useless for long-term attention and short-term.
from aot.
zhouweii234
commented on July 23, 2024
Thank you for your reply! By the way , do you use attn_mask?
from aot.
z-x-yang
commented on July 23, 2024
Long-term attention doesn't need any mask. The implementation of short-term attention is complicated. Since short-term attention has some processes related to the relative positions between pixels. Masking out the correlations out of feature boundary is necessary.
from aot.
Related Issues (16)
- About training detial HOT 2
- The sampling strategy during training HOT 4
- About the number of params of the model HOT 3
- Example video of results HOT 2
- May I ask the number of params of the LSTT block? HOT 1
- Question regarding Table 1 HOT 2
- Multi-view object segmentation HOT 1
- May I ask when you plan to release the code? HOT 1
- About the input dimensions of Long-Term Attention HOT 1
- Identification Embedding HOT 1
- About the X^m_l in Long-Term Attention HOT 1
- Do you use dropout in Long-Term Attention and Short-Term Attention? HOT 1
- Do you directly add the output feature of the backbone to the input of decoder? HOT 3
- About the LSTT block HOT 1
- The performance gains from image datasets (COCO, VOC, etc.) 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 aot.