# Tag Info

### What is difference between 'transfer learning' and 'domain adaptation'?

It seems wikipedia has the most concise answer: Domain adaptation is a subcategory of transfer learning. In domain adaptation, the source and target domains all have the same feature space (but ...
1 vote

### Does having the same background for all the images of a particular class increase a CNN model's ability to classify the images?

If you transform your images to all have the same background, you are removing noise from your data. This means a model trained on these transformed images may be more accurate on other images ...
• 422

### what is the memory usage of the VGG-net or any other neural networks?

For the detailed VGG memory footprint please take a look into: http://graphics.stanford.edu/courses/cs348v-18-winter/lectures/09_dnntrain.pdf, slide 22.
Accepted

### Does watermark/text on images at the same position influence the classification of images using CNN?

Yes, it can be a problem. A very similar example was used in the Unmasking Clever Hans Predictors and Assessing What Machines Really Learn paper by Lapuschkin et al (see below). They show an example ...
• 113k
1 vote

### Why is max pooling necessary in convolutional neural networks?

It really depends on the images. In some scenarios, Max pooling can take away too much info, resulting in worst performance that a CNN without max pooling. See this video for a surprising comparison ...
• 11

### What does it mean when all gradients of a neural network are 0?

Gradients all equal to zero does not necessarily imply any problem with the network. Both minima and maxima occur where the gradient is zero. So it’s possible that your network has arrived at a local ...
• 78.2k

### What does it mean when all gradients of a neural network are 0?

If you're using "tensorflow" and giving your model a batch make sure you put model(batch, training=True). If training isn't set to true then the gradient ...
Accepted

### Can self-supervised pretraining work with only labeled data?

Self-supervised learning is effective because it allows researchers to use much more data than they would have time/money to label. If you can't expand your training dataset using self-supervised ...
• 436
In theory, no. In practice, probably. The loss function you are minimizing is basically $$\min \ \frac{1}{N}\sum_{i=1}^{N}\sum_{k=1}^{K} (y_{ik} - f_k(x_i))^2$$ where $x$ is features, $y$ is $K$-...