Comments (3)
You could read some papers about 'self-supervised learning' on either images or videos, also the reference in our paper like OPN (Lee et al.), 3D-ST-Puzzle (Kim et al.).
These 98% and 88% results you mentioned are finetuned with a pretrained network: supervised pretrained on larger dataset like Kinetics (for I3D) or ImageNet (for two-stream), which requires expensive annotation.
Self-supervised learning doesn't require labels to learn the representation.
from dpc.
You could read some papers about 'self-supervised learning' on either images or videos, also the reference in our paper like OPN (Lee et al.), 3D-ST-Puzzle (Kim et al.).
These 98% and 88% results you mentioned are finetuned with a pretrained network: supervised pretrained on larger dataset like Kinetics (for I3D) or ImageNet (for two-stream), which requires expensive annotation.
Self-supervised learning doesn't require labels to learn the representation.
Thanks for your prompt reply ! But I think that it may require labels in the downstream classification task, since it has to output the highest score to match the label. Is this part require labels as supervised learning? If yes, then it is the same as supervised learning, right ? Then the reduceing performance may only due to the pretrained model? I'm curious :)
from dpc.
Evaluating the feature quality by finetuning on action classification task (requiring label) on smaller datasets is a conventional evaluation method for videos. Yes, the downstream task performance reflects the quality of the pretraining feature.
When comparing the self-supervised feature against the fully-supervised feature, the performance is not necessary 'reducing'. If you check the two-stream paper (Simonyan and Zisserman, 2014) Table 4, spatial stream on UCF101 result with ImageNet pretraining is 73%, but our self-supervised pretraining gets 76%. Self-supervised learning is very promising as you have unlimited data available from the internet.
from dpc.
Related Issues (20)
- Pretrained Networks missing some layer values HOT 2
- Experimental details of Table 1? HOT 6
- About the Contrastive Loss HOT 5
- negative examples HOT 1
- Not understanding why you take the last sequences and not the last samples of the sequences HOT 4
- Optimizing dataloading HOT 2
- Context and hidden state HOT 3
- Batch size per GPU HOT 3
- Sanity check: Classification after Self-Supervised training HOT 3
- gray scale performance HOT 1
- Pre-training on UCF101 HOT 1
- Tracking running statistics for BN HOT 1
- The necessary of train/validation split HOT 1
- Training Time HOT 2
- Link to pretrained model on UCF101 not working HOT 2
- Allow compatibility with latest torch (torch 18.1) HOT 2
- pretrained weight files aren't able to decompress HOT 2
- Possible reasons for loss function not going down HOT 6
- Why are you shuffling the sequence of images? HOT 2
- How to compute the self-supervised acc? 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 dpc.