Comments (4)
Hi~
This is an interesting question which I didn't notice before, but I think this may be explained from the perspective of feature norm.
Since the pre-trained network only learned the interface of the classifiers during the training process, and did not constrain the feature norm and the angle between the features, so high similarity score for two very different images is inevitable.
I think constrain the feature norm during training is essential to solve this problem like metric learning methods or feature normalization methods used in face recognition. If you do not want to re-train the model, post-process methods like l2-normalization may be helpful.
Min-max norm may make the similarity score smaller but will not change their relative order, I wonder if it will work.
Hope my answer can help you~
from pyretri.
Thanks for your reply. Deep metric learning is something worth trying. But most, if not all, papers use pre-trained CNN. L2 normalized is already used on every aggregation method. The high similarity score will make the false positive rate hard to control. Authors of those papers may not try query of an image out of the data set. Otherwise, the FP rate will be pretty high.
Min-max does not change the order of similarity scores. But if we do min-max globally within the whole data set, it may give a good reference for images out of the data set as query.
from pyretri.
Sounds reasonable. Thanks for your patient explanation :)
from pyretri.
I sent an email to the SPOC authors, and see how they answer.
from pyretri.
Related Issues (20)
- About the evalute HOT 2
- Err when running single_index.py HOT 1
- Whether to continue to train own datasets
- feature extraction issue for vgg model HOT 3
- I do not understand the usage of this parameter in oxford.yaml... HOT 2
- Will you continue to update this project?
- How to output confidence
- can we train it for custom retrieval task?
- unable to loop over dataloder. HOT 1
- use extract_feature.py extract indoor dataset feature.Model and state_dict portion miss match.Is that right? HOT 2
- MAP
- MAP for oxford is low HOT 1
- _pickle.UnpicklingError: invalid load key, '\xfe' HOT 1
- Custom data config setting
- UnicodeDecodeError while running python setup.py install HOT 1
- AssertionError at statement 'assert name in registry' in utils\builder.py HOT 1
- No feature extraction, no error messages
- make_data_json error query dataset HOT 1
- AttributeError: 'numpy.ndarray' object has no attribute 'pop' HOT 1
- Feature Extraction in Specific Layer
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 pyretri.