Comments (1)
This issue has been discussed in #13 .
The answer is that "Single label like imagenet is not influenced, because architecture surgery is designed for explainability task, and feature surgery compute the redundant feature as a common bias for each class. Thus, giving a same bias doesn’t change the rank and accuracy, instead it influences scores across images and benefits mAP for multi-label".
If you want to test classification mAP, the first step is to record cosine similarity from the original path with feature surgery, and then eval with gt using package like torchmetrics.
from clip_surgery.
Related Issues (20)
- onnx conversion HOT 1
- How to control the accurance of generate point? HOT 3
- Performance on classification datasets HOT 3
- About input sentence for SAM HOT 1
- Train/fine-tune CLIP_Surgery HOT 5
- mIoU evaluation for open-vocabulary segmentation HOT 3
- How can I make similarity_map_to_points select multiple objects! HOT 1
- question for equation 8 HOT 1
- Results of multi-label recognition HOT 2
- Question related to different image resolution from 224x224 HOT 1
- Questions about the open-vocabulary semantic segmentation. HOT 1
- Future work on medical imaging? HOT 1
- Could you release the implementation on ResNet Backbone? HOT 1
- Aquire about open-vocabulary segmentation implementation HOT 1
- Design of the category weight w. HOT 1
- About mSC HOT 1
- originality
- can you release the implementation of ECLIP?
- EVA-CLIP surgery?
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 clip_surgery.