Unanswered Questions
102 questions with no upvoted or accepted answers
12
votes
0
answers
436
views
Extending FaceNet’s triplet loss to object recognition
FaceNet uses a novel loss metric (triplet loss) to train a model to output embeddings (128-D from the paper), such that any two faces of the same identity will have a small Euclidean distance, and ...
CommunityBot
- 1
6
votes
0
answers
154
views
Are there any easy ways to create annotated training images for object detection?
For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
- 42.4k
3
votes
0
answers
72
views
How are Ground truth provided to each Pyramid map in RetinaNet or YOLOv3 Paper? How is the mapping of Feature Pyramids done to Ground Truth
SO the YOLO V3 and RetinaNet both uses the Feature pyramids which look something like this:
(except b and e which have one ...
- 263
3
votes
0
answers
59
views
If random rotations are included in the data augmentation process, how are the new bounding boxes calculated?
When studying bounding box-based detectors, it's not clear to me if data augmentation includes adding random rotations.
If random rotations are added, how is the new bounding box calculated?
- 42.4k
3
votes
0
answers
39
views
Defect Detection System using Deep Learning
What is the general approach to defect detection in deep learning?
Would the approach be better if we try to learn the positive images (defects in images) as much as possible or we try to learn the ...
- 131
3
votes
0
answers
125
views
Does Retina-net's focal loss accomplish its goal?
Taking out the weighting factor we can define focal loss as
$$FL(p) = -(1-p)^\gamma log(p) $$
Where $p$ is the target probability. The idea being that single stage object detectors have a huge ...
- 2,399
3
votes
0
answers
65
views
How should I build an AI that quickly detects falling game assets on screen?
I want to build an AI that plays a simple android game.
The game is just a one at a time object falling, some times at an angle. The AI needs to recognize the object and to decide whether to swipe ...
- 42.4k
3
votes
0
answers
30
views
How to voxelize multiple frames at the time and append them together?
I'm trying to implement this approach for object detection and tracking.
In this approach, the first step is voxelize each frame to construct a 3D tensor, the second step is to append multiple voxels ...
- 42.4k
3
votes
3
answers
753
views
Face liveness detection using face landmark points
How to detect liveness of face using face landmark points?
I am getting face landmarks from android camera frames. And I want to detect liveness using these landmark points.
How to tell if a human ...
CommunityBot
- 1
2
votes
0
answers
146
views
Indoor elements detect from floor image
I have a large collection of floor plans that I need to convert into indoor maps by extracting walls as lines, doors as lines, and rooms as polygons. Currently, I do this process manually.
The floor ...
- 101
2
votes
2
answers
2k
views
How does YOLO detect the object when the object is in multiple grid cells?
I have been reading various articles and watching videos on YouTube, but I can't seem to understand one thing.
How does YOLO make a bounding box for an object if it is in multiple grid cells? For ...
CommunityBot
- 1
2
votes
0
answers
115
views
What would be a reasonable option for clustering for unknown number of clusters and a lot of outliers?
I am implementing the CV detection pipeline with the use of SIFT and KNN Matcher.
Image keypoints matched to the query keypoints produce the following image:
The matched objects have a lot of key ...
- 42.4k
2
votes
0
answers
60
views
Can a GIoU loss (generalized intersection over union) be used after an STN module (spatial transformer network)?
I have a model that uses an STN module for number detection and Mean Squared Error loss. But I would like to replace it for GIoU, because MSE doesn't take into account how much of the target area has ...
- 4,062
2
votes
0
answers
83
views
Which method can accurately detect circular/angular shapes? (attached example)
Is there a method to detect shapes like these accurately and efficiently? I have tried the OpenCv Haar Casacade Classifier which does not work well. These shapes should all be the same class object ...
- 21
2
votes
0
answers
116
views
Vector input to CNN for object detection
I am training a 3D object detection network (Retinanet-based as of the moment) for re-detecting tracked objects. I would like to be able to add the velocity vector of the tracked object as an input to ...
- 121