Comments (3)
My understanding is that the cross-correlation matrix only considers the decorrelation between a 2 augmentations of same image.
The empirical cross-correlation matrix is computed from all images in a batch. We cannot compute the cross-correlation matrix from (2 augmentations of) a single image.
Consider C[i, j], the value in the i-th row and j-th column of the cross correlation matrix C. C[i, j] measures the correlation between the i-th and j-th feature of our 8192 dimensional representation. If you want to know how correlated the i-th and j-th feature are, you need to know the values of the i-th and j-th feature for many samples. We use a batch of samples to estimate this correlation.
I hope that makes it clear.
from barlowtwins.
I also holds a problem of understanding, there is no interaction between different samples in the batch.
for example in simclr then is s_ij, which is cosine distance between two samples in the batch. But in your work as I undeerstand from eq1,2 , each sample in the batch is only interects with itself . I'm missing something?
from barlowtwins.
I also holds a problem of understanding, there is no interaction between different samples in the batch.
for example in simclr then is s_ij, which is cosine distance between two samples in the batch. But in your work as I undeerstand from eq1,2 , each sample in the batch is only interects with itself . I'm missing something?
In equation 2, when calculating correlation term, there are sums across batch dimension. So there are interaction among different samples.
It's not like SimCLR to have pairwise interaction. It's an interaction through statistics among batch.
from barlowtwins.
Related Issues (20)
- Issue loading checkpoint.pth file HOT 1
- Augmentation Distribution HOT 1
- Will BarlowTwins overfit on the training data?
- When using the own dataset, loss is around 10,000 HOT 8
- About the last normalization layer HOT 1
- Dose we can add distorted image, like Y_a, Y_b, Y_c?
- A question on the BT loss with Batch Norm layers HOT 4
- Start index for each epoch HOT 3
- weight update for step=0,epoch=0 get's missed. HOT 2
- Applications on one-dimensional signal datasets HOT 4
- Where could we find the "reproduced version" of the other SSL methods HOT 1
- Question about Fig. 4 in the paper HOT 4
- Quality of Embeddings
- Possible bug on the loss computation HOT 1
- Error in saving resnet50.pth HOT 2
- efficiency proposal HOT 1
- NaN's introduced during training.
- providing the linear ImageNet classifier weights
- Pre-training model for CIFAR
- Why c.div_(self.args.batch_size) is needed? HOT 1
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 barlowtwins.