Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [domain-adaptation]

12 questions
5
votes
1 answer

What is the difference between BatchNorm and Adaptive BatchNorm (AdaBN)?

I understand that BatchNorm (Batch Normalization) centers to (mean, std) = (0, 1) and potentially scales (with $ \gamma $) and offsets (with $ \beta $) the data which is input to the layer. BatchNorm follows this formula: (retrieved from arxiv-id…
DaveTheAl
  • 493
  • 1
  • 5
  • 11
3
votes
4 answers

Discrepancy between training set and real-world data set: domain adaptation?

I have read in literature that in some cases the training set is not representative for a real-world dataset. However, I cannot seem to find a proper term describing this phenomenon; what is the proper term to address this problem? Edit: So far I…
Archie
  • 863
  • 7
  • 20
3
votes
2 answers

Training data from different sources

I am working on a binary classification problem. My data contains 100K samples from two different sources. When I perform the training and testing on data from the first source I can achieve classification accuracy up to 98% and when perform…
Bashar Haddad
  • 1,939
  • 1
  • 13
  • 17
3
votes
2 answers

Dealing with an apparently inseparable dataset

I'm attempting to build a model/suite of models to predict a binary target. The exact details of the models aren't important, but suffice to say that I've tried with half a dozen different types of models, with comparable results from all of…
Chinmay Kanchi
  • 131
  • 3
1
vote
1 answer

What is the difference between Multi task learning and domain generalization

I was wondering about the differences between "multi-task learning" and "domain generalization". It seems to me that both of them are types of inductive transfer learning but I'm not sure of their differences.
Milad Sikaroudi
  • 113
  • 4
1
vote
0 answers

Latent space for cross domain numerical features

I would like to find the shared latent space between two set of features. I have source and target domain features already extracted from images. I have 4 set of feature vectors for normal and abnormal source and target domains. I would like to…
Minnie
  • 21
  • 1
1
vote
0 answers

Close set and open set classification at the same time

Is it possible to use a neural network(or another approach) to classify image based on trained data and at the same time if new image classes are introduced in the test set it should classify those unseen images(open set data) to new classes(kind of…
Rambo_john
  • 13
  • 4
1
vote
1 answer

Train on multi-domains, then fine-tune on specific domain

Would it make sense to first train a model on images from multiple domains, and then do "fine-tuning" on one specific domain to improve its performance on it? For instance, one could train an object detector based on cars camera recorded in NYC,…
guillaumefrd
  • 11
  • 1
0
votes
0 answers

How can I use transfer learning to predict height given age in Japan, using a model developed with USA data?

Suppose I have a (training) set of $n$ observation $\{(Y_i^{(U)},X_i^{(U)})\}_{i=1}^n$ of age $X_i^{(U)}$ and height $Y_i^{(U)}$ from people in the USA. Now suppose I also have a (test) set of $m$ observations $\{X_i^{(J)}\}_{i=1}^m$ of age…
sonicboom
  • 101
  • 1
0
votes
1 answer

How to measure the performance of a domain adaptation /Transfer learning technique?

Given that the performance you achieve depends on how far the target from the source domain is, how can you judge the performance of an algorithm?
Alex
  • 135
  • 5
0
votes
1 answer

Why does increasing the training set size not improve the results?

I have trained a model on a training set, which is not that big (overall around 120 true positives, and of course lots of negative examples). What I am trying to do is to improve the results by increasing the data size. I tried two approaches: I…
user1419243
  • 109
  • 3
0
votes
0 answers

Fine-Tuning / Transfer learning results in worse performance

My task is creating a model for QA-purposes. I have only ~200 samples on a specific domain of questions. Using a pretrained like DeBERTa without any further changes results in f1 scores of ~35%. To further improve this, I tried to train the model on…
max245905
  • 1