Comments (3)
Hi @tommying, thank you for your interest!
- The cosine similarity formula u * v / ||u|| * ||v|| itself does not imply anything about the norm, as the norm of u (so as v) affects both the numerator and denominator. However, we hypothesize that the SimCLR objective implicitly increases the norm, as it is hard to decrease the Euclidian distance of the features u and v; hence the model pushes both features (yet keeping the Euclidian distance) to decrease the cosine similarity.
- Note that sim(z(x_m), z(x)) ||z(x)|| = (z(x_m) * z(x) / ||z(x_m)|| * ||z(x)||) * ||z(x)|| = z(x) * (z(x_m) / ||z(x_m)||), where z(x) is f_sim and z(x_m) / ||z(x_m)|| are P.axis in our code.
- SimCLR (Eq. (2)) only pushes unshifted negative batches B, but CSI (Eq. (3)) also pushes shifted negative batches B_S. By substituting B to B_S in Eq. (2), you can derive that the objective is changed from L_con(x^1,x^2,B) to L_con(x^1,x^2,B_S). Also, Eq. (4) is used to further discriminate the shifting transformations. Intuitively, there are no reason to not use the additional shifting transformation labels, and it indeed improves the performance as we show in our ablation study (Table 7a).
Best regards,
from csi.
thank you, sir.
from csi.
- I also confused about problem 1. The first part of Eq. (6) is intuitive: the OOD samples' embedding is far from the ID samples' embedding, so the sim(z(x_m), z(x)) would be small if x is OOD.
However, @sangwoomo explains that the model pushes both features' norm to decrease the cosine similarity. I am confused that how the difference of ID & OOD samples is shown in the term ||z(x)||? Could you explain it more?
- Besides, "we hypothesize that the SimCLR objective implicitly increases the norm" seems not to explain the reason why the term ||z(x)|| is smaller for OOD samples.
Very thanks!
from csi.
Related Issues (20)
- Can you share the implementation detail for baseline?(Cross-Entropy) HOT 3
- Why did you do the rotation transformation firstly and then apply the simlcr_aug? HOT 1
- batch size HOT 4
- The result of using the checkpoint of unlabeled ImageNet-30 HOT 3
- CSI/training/unsup/simclr_CSI.py HOT 1
- Error while running the training script. HOT 1
- GPU requirement for training ImageNet model HOT 1
- About how to get result for noise condition
- How to define the joint_labels
- ImportError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.21' not found HOT 1
- The hyper parmeter of Rot(resnet18) and Rot+Trans(resnet18)
- Reproducing results for Cifar100 ens multi-class
- How can i train it on my own dataset? HOT 10
- GPU requirement for training One-class ImageNet-30
- Some questions about Supervised_NT_xent
- baseline code?
- cannot reach the results when removing the four-way rotation classifier
- why use the hfilp() function during training? What does it do?
- Model is provided extra arguments.
- Problem
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 csi.