Comments (2)
Hi @GuangyuanLiu1999 ,
Thanks for showing interest in our work. The class embedding files can be:
- taken directly as a reference from previous repositories that provided them, like our repository, PL-ZSD, etc.
- generated yourself by downloading pretrained word2vec/glove/fasttext (whichever embedding you need) embeddings and obtaining the specific vectors for each object class following this tutorial.
- Note that in both these cases, there might be differences in the vector elements you obtain, as some people apply different vector normalizations before using them as semantic vectors.
- Moreover, to follow our work you need to have semantic vector of a "background" class which can be obtained from our given fasttext.npy. You might obtain that semantic vector even yourself, for example, by averaging the vectors of all object classes[1], or by assigning a fixed vector[2,3]. However, performance might not be the same.
To answer the indexing issue, before the training of our cWGAN starts, in trainer.py, we first load the class embedding matrix, for which utils can be found at generate.py. The mapping of classes with labels/ids can be found at splits.py.
[1] Rahman, Shafin, Salman Khan, and Fatih Porikli. "Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts." Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part I 14. Springer International Publishing, 2019.
[2] Bansal, Ankan, et al. "Zero-shot object detection." Proceedings of the European Conference on Computer Vision (ECCV). 2018.
[3] Zhu, Pengkai, Hanxiao Wang, and Venkatesh Saligrama. "Don't even look once: Synthesizing features for zero-shot detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.
from zsd-sc-resolver.
Hi @GuangyuanLiu1999 ,
Thanks for showing interest in our work. The class embedding files can be:
- taken directly as a reference from previous repositories that provided them, like our repository, PL-ZSD, etc.
- generated yourself by downloading pretrained word2vec/glove/fasttext (whichever embedding you need) embeddings and obtaining the specific vectors for each object class following this tutorial.
- Note that in both these cases, there might be differences in the vector elements you obtain, as some people apply different vector normalizations before using them as semantic vectors.
- Moreover, to follow our work you need to have semantic vector of a "background" class which can be obtained from our given fasttext.npy. You might obtain that semantic vector even yourself, for example, by averaging the vectors of all object classes[1], or by assigning a fixed vector[2,3]. However, performance might not be the same.
To answer the indexing issue, before the training of our cWGAN starts, in trainer.py, we first load the class embedding matrix, for which utils can be found at generate.py. The mapping of classes with labels/ids can be found at splits.py.
[1] Rahman, Shafin, Salman Khan, and Fatih Porikli. "Zero-shot object detection: Learning to simultaneously recognize and localize novel concepts." Computer Vision–ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2–6, 2018, Revised Selected Papers, Part I 14. Springer International Publishing, 2019. [2] Bansal, Ankan, et al. "Zero-shot object detection." Proceedings of the European Conference on Computer Vision (ECCV). 2018. [3] Zhu, Pengkai, Hanxiao Wang, and Venkatesh Saligrama. "Don't even look once: Synthesizing features for zero-shot detection." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020.
Thank you very much for your serious reply. I will seriously follow your prompts to do experiments, and I would like to express my heartfelt thanks to you again.
from zsd-sc-resolver.
Related Issues (20)
- Setting batch size
- The test result of detector trained only on seen classes HOT 23
- Training on custom data HOT 2
- class embedding vector for custom data HOT 4
- Custom Data HOT 1
- low accuracy on unseen classes HOT 1
- when classifier is trained
- is train_unseen_classifier.py missing HOT 1
- how to generate test npy for unseen classes HOT 2
- custom dataset tune HOT 2
- Pascal VOC data split HOT 2
- NaN metrics during Epoch 1 on coco2014
- inference to single image HOT 1
- num_classes for first step HOT 3
- Do you have a minimal environment YAML file? HOT 1
- Do you still have the weight file obtained by executing the fifth step HOT 2
- Do you think you'll ever migrate your code to the latest stable versions of mmcv and mmdetection? HOT 13
- Some hesitations related to background class label index HOT 5
- Confusion about validation metrics for zero-shot detection. HOT 3
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 zsd-sc-resolver.