Comments (1)
Yes, you are right. The attention module designed here is different from the attention module design in NLP task. We don't necessarily need to follow the attention module design with key and query components, as long as it follows the idea of "attended features", then it can be called attention-based methods.
from mtan.
Related Issues (20)
- depth and segmentation label in cityscape HOT 1
- NYUv2 surface normals grey boundary HOT 1
- Missing items in cityscapes/val/label_19 HOT 2
- Training with my own dataset HOT 16
- Definition of multi-task loss function HOT 5
- Training MTAN-DeepLabv3 HOT 10
- About the instantiation of the model HOT 1
- DWA HOT 1
- The para Temperature of DWA HOT 6
- How do you pre-process NYUv2 dataset? HOT 7
- about the uncertainty loss HOT 4
- about visulization of the result HOT 1
- Avg Cost accumulation HOT 2
- why dwa didn't consider common scale of gradient? HOT 8
- 关于Attention Module的设计 HOT 4
- results inconsistency HOT 19
- Question about the pre-processed cityscapes HOT 5
- DWA的loss梯度爆炸问题 HOT 2
- Question about the structure of the encoder_block_att. HOT 2
- Used Mtan on depth estimation and object detection HOT 5
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 mtan.