Comments (7)
from medicaldetectiontoolkit.
For common object detection like COCO, MaskRCNN works better than RetinaNet. But their configurations are not exactly the same, I have to admit. One has additional instance labels and the other one uses focal loss.
In my opinion, a one-stage model is more or less like an RPN. The second stage can eliminate false positives and fine-tune the regression boxes.
Do you think this explanation makes sense for lesion detection?
from medicaldetectiontoolkit.
The resampling operation (RoiPool / RoiAlign) was initiated to enforce scale-invariance of box-proposals. This only makes sense in natural images, so basically you want to re-scale a big car and a small car to the same size to facilitate the classification task for the classifier head. Here, it makes sense to get rid of the scale information, because it is an artifact caused only by varying distances between camera and objects which contains no semantic information. In medical images we assume that the distance between camera and object is the same over the entire image, thus the scale-information contains semantically relevant information such as size of a tumor. Intuitively, you would not want to cancel this out in your model.
There is another reason, why the second stage could rather hurt performance than boost it: As there is no reason for the re-sampling operation, there is also no real benefit from the second stage operations, because no new information is gained/processed. In an ideal decision process, you would want to gather all information possible and then take one informed decision (this is what happens in a one stage detector), as opposed to a sequential decision process, where information gets discarded along the way possibly throwing away relevant bits, before taking the ultimate decision (two stage models).
So in fact, there are two reasons why one stage models should intuitively be superior to two stage models on medical images.
Do you agree?
from medicaldetectiontoolkit.
Thanks, I think this makes good sense. The scale information a priori can be used by the model. But does this mean there's risk of overfitting if the scale distribution of training set is different from the test set? I think this is possible for medical imaging data.
from medicaldetectiontoolkit.
yes good point. If your test data contains lesion sizes not apparent in the training data, you might be better off using 2 stage detectors, because here the re-sampling helps you to overcome the domain shift. I would, however, call this a rather special case, as arguably most of machine learning apps (that are not specifically dealing with domain shifts) assume equal distributions in training and test data.
from medicaldetectiontoolkit.
Yes, I agree. Different distributions between training and test set is quite challenging and only a two-stage detector could be still no enough.
Thanks again for the great explanation, and this nice repo.
from medicaldetectiontoolkit.
glad I could help. thanks for your feedback.
from medicaldetectiontoolkit.
Related Issues (20)
- Compile Cuda Functions Help
- Question about "min_det_thresh" in test plotting
- troubles with MultiThreadedAugmenter HOT 2
- Problem with one class training HOT 4
- How could I preprocess my own nii data? HOT 2
- out of memory ConvertSegToBoundingBoxCoordinates
- How should I prepare the dataset? HOT 1
- inference issue
- Compiling CUDA functions for Titan RTX HOT 1
- data_load is very very very slow?
- how to improve the speed of test?
- Batch generation error on my customized dataset HOT 1
- KeyError when trying to train in toy_exp HOT 3
- TypeError: crop_and_resize_forward expected 7 arguments, got 8 when running on cpu
- How can I only evaluate based on the ground-truth bounding box? HOT 1
- When using batch_generator, where should I put "boxes_coords" in? HOT 1
- only a single thread working in "MultiThreadedAugmenter " !
- How to write U-Net Deep Learning code dealing with ".tiff" images?
- Project dependencies may have API risk issues
- Can you share the preprocessed LIDC dataset,Thank you HOT 1
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 medicaldetectiontoolkit.