Comments (7)
Hi Amit, I read your brief and interesting post about semi-supervised learning, would you suggest me to continue with this area or GANs for PhD research?. My master's background is from GANs but I found this area very interesting. will appreciate your suggestion Thanks!
from blog-comments.
@israrbacha A Ph.D. research topic is something you would spend years on and is a very personal choice. So I don't think I can give you a definite answer.
That said, semi and self-supervised learning are indeed active research areas right now. Maybe you could explore existing literature that utilizes GANs for semi/self-supervised learning and see if that interests you. That way you can combine your existing background of GANs with your interest.
from blog-comments.
Hi Amit, thanks for great article. I am working on my diploma thesis in the field of Self-supervised learning and I would like to ask, if you know about any code how to do transfer learning to downstream task. I read a lot about pretext-tasks (also on your other article) so now I know some ways how they work, but I would like to know, how to transfer that knowledge into downstream task (probably to instance segmentation), but can be also any other. I would appreciate code example to understand it better. Because I read about theory in this article :)
So to sum it up - do you know a way how to do pretext task and then downstream task with aim to do instance segmentation (for example to mask-r-cnn) in code? Thanks!
from blog-comments.
@timothyvanco Yeah, there is pytorch-lightning-bolts. They've implemented most standard models for self-supervised learning.
I haven't worked on instance segmentation problems, so not sure. But, I think you can use it by swapping the backbone network with an SSL model and see how much performance improvement that gives.
from blog-comments.
Hi Amit, thanks for great article. Currently, I am playing around with jigsaw puzzles in this paper https://arxiv.org/pdf/1603.09246v3.pdf. After finishing pretext task, how to do downstream task using labeled dataset for classification task ? do we need to make 9 patches of image or just pass the whole images ?
from blog-comments.
@ramdhan1989 For downstream task, the paper initialized AlexNet with weights from the pre-text task and used that for classification. We don't need to make 9 patches.
See the bolded part of comment of Figure 3 in the paper.
from blog-comments.
Hello, Nice blog
Might you know if it works on different tasks, e.g. Segmentation or object detection for the downstream task?
from blog-comments.
Related Issues (20)
- 2020/06/google-colaboratory-tips/ HOT 6
- 2020/06/fastapi-vs-flask/ HOT 17
- 2020/03/illustrated-simclr/ HOT 32
- 2020/08/information-retrieval-evaluation/ HOT 6
- 2020/06/fasttext-embeddings/ HOT 8
- vscode-on-colab/ HOT 25
- 2020/02/tensorflow-hub-for-transfer-learning/
- 2020/02/albert-visual-summary/ HOT 3
- keyphrase-extraction/ HOT 1
- 2020/03/fixmatch-semi-supervised/ HOT 5
- interactive-sentence-embeddings/ HOT 2
- 2019/12/migrating-to-pathlib/ HOT 3
- 2020/07/semi-supervised-learning/ HOT 6
- 2020/04/deepcluster/ HOT 7
- regex/ HOT 6
- 2020/03/illustrated-pirl/ HOT 1
- 2018/10/django-orm-for-sql-users/ HOT 2
- 2020/04/illustrated-self-labelling/ HOT 4
- 2019/03/automate-ssh-commands/ 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 blog-comments.