Comments (4)
@HobbitLong As I don't know if there is any timeline on this issue and just to be sure to understand everything correctly to replicate the NYU RGB-D experiments the following steps would be required to replicate them wouldn't they?
- Initialize the different models per modality
feat_l, feat_ab, feat_depth = model(inputs)
- Create different contrast objects for the different pairs (e.g. in the core view scheme contrast_l_ab, contrast_l_depth)
2.1. This would enable something like
out_l, out_ab = contrast_l_and_ab(feat_l, feat_ab, index)
out_l_2, out_depth = contrast_l_and_depth(feat_l, feat_depth, index)
- For each of the modalities one need to create a criterion object (twice for the core modality "L"). Which would lead to something like
l_loss_from_l_and_depth = criterion_l2(out_l_2)
depth_loss_from_l_and_depth = criterion_depth(out_l_2)
- And then add the results from above to the general loss term.
Is this the correct way to go forward?
How exactly did you do the patched based training on the "L" modality? Could you provide some hyper-parameters for that?
Thanks for the otherwise very nice repo.
from cmc.
@meyerjo ,
To your question, we used "patch-based contrastive objective" for this task, please refer to section 3.5.2.
That being said, for each of the modality, we extract global feature as well as local feature. Then we contrast between (1)global feature from modality A to local feature from modality B and (2)global feature from modality B to local feature from modality A. The way we build this global-local contrastive loss is exactly the same way s DIM paper. The code for this loss can be found here.
The way of extracting global local feature can be found here.
And then we sum up those pair-wise loss as described in our paper.
from cmc.
@HobbitLong thanks for this additional info.
Just to confirm, the use of a patch-wise method here is only motivated by a small dataset?
I am also trying to find an explanation of the global/local feature concept in your CMC paper - is this a deviation from the method presented there?
Many thanks!
from cmc.
@jnyjxn ,
Yes, NYU dataset only has less than 2k images.
This is different from the ImageNet experiment, but has been described in the supplementary of the paper.
from cmc.
Related Issues (20)
- Weight shape in Linear classifier HOT 1
- Train/Test split when training linear classifier (ImageNet) HOT 3
- Gpu memory heavy on gpu0 HOT 1
- mean std value for LAB/YCbCr normalization HOT 1
- How to prevent positive sample is sampled by AliasMethod? HOT 1
- Format of dataset HOT 2
- index drawn by AliasMethod is not on the same gpu as the model HOT 1
- About the training epochs for ImageNet-1K
- question about shuffle_ids
- Training Loss Doesn't Improve for CIFAR10
- pretrained model of ResNet50v1
- Feature Tensor Shape Question HOT 1
- how to use the pretrained MoCo
- Protential memory leak when training?
- Modified AlexNet architecture for STL-10 dataset
- question about input image
- Questions about NCEAverage.py
- How can it be used for more than two views datasets?
- Pre-trained model for Video task HOT 1
- CMC for small custom dataset
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 cmc.