Comments (3)
Hi, we tried some elements of that direction but stopped when 4D convolutions appeared to be too slow to work on our relatively high-res images. And we had to keep them high-res because we wanted to detect small objects.
However, we definitely did not experiment with this direction sufficiently.
from os2d.
Thanks for answering.
By the way, if I want to improve the generalization of the model, it is a good choice to train it using the COCO or the object365 dataset?
I tried the v2 model in some unseen object, it is not very good if the object is large. So maybe a large dataset is better?
Some new paper of one-shot object detection like "Balanced and Hierarchical Relation Learning for One-shot Object Detection" trained using the coco perform better in the large object.
from os2d.
Our model was designed with mostly intance-level recognition in mind, which does not go too well with broad categories as in COCO. Another thing to keep in mind is that the current linear transformation model does not suit non-rigid objects (can still work to some extend). I'm actually quite sceptical on the one-shot setting for broad classes like in COCO. It looks like for these kind of things one can easliy collect lots of annotation to get regular detectors to work. One-shot or few-shot formulations are better suited elsewhere in my opinion.
To deal with large objects with our model, I recommend to look carefully at the image resolution. The model works best when the size of object to detect (in pixels) rouhly matches the size of the template images (which is built into the model weights).
from os2d.
Related Issues (20)
- Same class images with different class_ids get different results? HOT 1
- Attributes of grozi.csv HOT 3
- Error on using multi GPU setting HOT 2
- What is 3264 in the src? HOT 2
- Cannot find 'net' in the checkpoint file HOT 2
- Need for OrderedDict HOT 2
- CUDA out of memory HOT 4
- Security alert from dependabot HOT 3
- Multi-GPU training for detector HOT 6
- Segmentation fault HOT 4
- Error in visualisation HOT 1
- New form of evaluation HOT 3
- some new ideas about YOLO to os2d HOT 1
- Memory Leak when training and long evaluation time HOT 3
- Long Evaluation time and question about environment for training HOT 4
- Dataset scales when training with custom data HOT 2
- Evaluation Dataset HOT 1
- Unable to reproduce correct results from demo.ipynb HOT 2
- read image with cv2.imread
- how can I train my custom dataset base on OS2D V2-train model?
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 os2d.