New answers tagged computer-vision
2
votes
Term for algorithms that are not trained
The word "Artificial intelligence" refers to machines being able to have intelligence that of humans/animals. The meaning of the word was even discussed on this site. So it's up to your ...
- 176
1
vote
Term for algorithms that are not trained
How about handcrafted -as you mentioned-? In the following question it is opposed to learned.
https://datascience.stackexchange.com/questions/54390/what-is-the-difference-between-handcrafted-and-...
0
votes
What papers can I read that explore model performance vs dataset size?
I found a paper that might be helpful. The paper is titled “Sensitivity Analysis of Dataset Size vs. Model Performance”. It discusses the relationship between training dataset size and model ...
2
votes
Accepted
Are CNNs exactly translation invariant with global max/average pooling layers?
Your intuition is correct, when you apply many local feature detectors (convolutions) and throw the results into one big pot (any global pooling), only the amount of detected features matters, not ...
- 1,317
1
vote
Are platformer games, with the camera centred on the character, examples of egocentric vision?
At the time, this probably referred to what we call an POV or first person view. It was applied to head mounted cameras. This term was developed a long time ago to describe something that didn't have ...
- 111
2
votes
How to detect outlier images?
I agree with Triple S' answer, but as a preprocessing step I suggest to use some pre-trained image classification network without the last fully-connected layer. This will give you robust features ...
- 605
3
votes
How to detect outlier images?
Hi there @pookie you can approach this problem using unsupervised anomaly detection techniques. One such technique is to use an autoencoder neural network.
The idea is to train an autoencoder on a ...
- 31
0
votes
How do I know if image after image enhancement is better than before? (Image Preprocessing)
As said in other answers, it can be very difficult to quantify "better" and this depends on your problem domain. However, we can quantify "different" (with respect to the original ...
0
votes
How do I know if image after image enhancement is better than before? (Image Preprocessing)
"Better" has a very wide definition. Is it faster? Better accuracy? Better precision? First, you need to define what you mean by "Better"
In general, it depends on your task (...
- 2,621
2
votes
Does the position of the tokens in Vision Transformer matter?
It does not matter.
Although, I can imagine a situation where it could matter a bit - when position embeddings are not learnt but calculated and fixed like in the original transformer (Attention is ...
- 71
3
votes
Accepted
Does the position of the tokens in Vision Transformer matter?
It should not matter. To explain why, we need to understand how a transformer works.
Transformers were originally designed for language models. They compute a self attention matrix, which is a fancy ...
- 2,005
0
votes
Accepted
Why does CLIP use a decoder-only transformer for encoding text?
I believe because Decoder-only basically cuts down the model size in half, and has also shown empirically to be better.
In the original Transformer paper, the evaluation task was about Machine ...
- 1,007
0
votes
How do you name your deep learning training outputs?
You could use the most important distinctions to build a folder structure. For example I experiment with multiple model architectures (resnet, mobilenet, ...) and different types of classification (...
0
votes
How does general image background removal AI work?
Background removal is technically known as image matting. It is similar to segmentation, but it is a regression problem. The objective is to predict the alpha matte, which separates the foreground and ...
- 101
Top 50 recent answers are included
Related Tags
computer-vision × 482deep-learning × 153
convolutional-neural-networks × 125
machine-learning × 92
object-detection × 65
neural-networks × 63
image-recognition × 51
image-processing × 51
object-recognition × 31
image-segmentation × 25
classification × 24
papers × 24
yolo × 24
terminology × 21
reference-request × 20
python × 18
tensorflow × 15
transformer × 12
training × 11
datasets × 10
data-preprocessing × 10
algorithm-request × 10
comparison × 9
keras × 9
generative-adversarial-networks × 9