Comments (2)
So the first two indices of u corresponds to the N x N scores across the entire batch. The diagonal corresponds to scores from the same image, off-diagonal are scores between two different images from the same batch. Positive samples are from the same image, and we "draw" these by simply pulling out the diagonal component of the positive scores. The negative samples are "drawn" by pulling the off-diagonal elements from the negative scores.
Hope that helps.
from dim.
Thanks for your explanation!
from dim.
Related Issues (20)
- Table 3. CPC comparision, ResNet 50 design choice HOT 1
- Where is the discriminator network parametrized by omega? HOT 1
- Questions about prior matching part HOT 1
- A question about the discriminator in CIFAR10 on a DCGAN architecture - local. HOT 1
- High level question about discriminator HOT 1
- Question about sampling the x' (negative samples) & code. HOT 4
- MINE as an estimation of Mutual Information between input space and latent representation HOT 1
- Can I use your code on a small sample dataset?
- I'm having No module named 'cortex_DIM' error HOT 1
- KeyError: '`torchvision` not found in .cortex.yml data_paths'
- Something about Eq.4 in your paper that I can't understand
- How to understand mutual information in deterministic deep networks?
- The version of cortex
- A TypeError in running
- Using new dataset
- Question about prior matching HOT 2
- Hi Masoudpz, HOT 1
- questions about bi-level optimization in prior matching loss
- controller = Controller(inputs=dict(inputs='data.images'), **models)
- Figure 4: Scatter plots of M I(x; y) versus JSD(p(x, y)||p(x)p(y))
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 dim.