Comments (1)
Hi,
It's been a while but better late than never.
It never occurred to me to actually pick the top-k locations during inference. It might indeed be beneficial in comparison to sampling. Something to keep in mind would be that this would no longer be an unbiased approximation so it might introduce some bias especially if the attention is very peaky.
Regarding, ATS-10 vs ATS-50 we use the same number of patches both during training and inference.
Having the model predict the patch size would be an interesting extension to this paper. For instance, one could predict two Gaussian random variables for patch width and height and then use the same math to approximate the average feature integrating over the patch size values.
Cheers,
Angelos
from attention-sampling.
Related Issues (20)
- RuntimeError: Couldn't compile and install ats.ops.extract_patches.libpatches HOT 4
- file not found HOT 2
- Allow use of a patch generator HOT 5
- Offsets for extracting patches HOT 4
- C++ versions less than C++11 are not supported
- Suggestion of Environment (OS, package version, etc.) HOT 1
- Implementation of eq. 12 HOT 2
- Validation Accuracy Does not Change HOT 1
- MNIST noise overlaps signal
- expected_with_replacement
- Installation document no longer available
- Segmentation fault (core dumped) HOT 2
- What's the softmax temperature? HOT 1
- pip install runtime error: Couldn't compile and install ats.ops.extract_patches.libpatches HOT 4
- Unable to install on Macbook pro HOT 4
- It's not learning HOT 2
- Extracting weird patches HOT 6
- Batch size for all the experiments in the papaer HOT 2
- What is the role of "receptive field"? 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 attention-sampling.