Comments (1)
Thank you for your interest in our work!
It may be because the resnet features are not discriminative enough for shoes. You can try changing the semantic loss features to DINO ViT, In a related paper the authors seem to perform good segmentations on shoes https://dino-vit-features.github.io/ with it. I would also experiment with a stonger equivariance loss eg. maybe with random_mirror enabled and with higher loss coefficient.
from unsup-parts.
Related Issues (13)
- Looking forward to the code HOT 6
- Not working for batch size=2 HOT 1
- Issue during training with utils.deepcluster_vgg16 HOT 1
- Keypoint names or part names?
- Request for the evaluation code
- About the source code HOT 2
- Apply for the code~ HOT 2
- Inspirational work! Question about visual consistency loss HOT 1
- Can you release profiles for PASCAL-PART datasets?
- `FileNotFoundError: [Errno 2] No such file or directory: 'models'` HOT 1
- Unable to reproduce the result as paper reported HOT 1
- Regarding mapping of 15 Gt Keypoints to 4 parts
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 unsup-parts.