Skip to main content

Questions tagged [out-of-distribution]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
1 answer

Is there a OOD detection method treats OOD samples as another class in multiclass classification?

A simple way I can think of to detect OOD samples is to treat them like another class in a multiclass classification problem. For example, with MNIST, we would modify the network to predict another ...
Lewis Morrow's user avatar
1 vote
1 answer

Applying classification model when training and inference populations are different

I am looking for ways of estimating or mitigating the risk of applying a classification model (say logistic regression for simplicity) in a certain population (the inference set) that is known to be ...
jpsca1293's user avatar
4 votes
0 answers

Is there a difference between out-of-domain and out-of-distribution?

When I research papers on the generalisability of ML models, both terms "Out of Distribution" and "Out of Domain" pop up. Are these essentially the same? In my understanding, yes. ...
amsulic's user avatar
  • 61
0 votes
0 answers

Distribution shift, model shift and training error

Is there any existing result that characterizes how training error changes (increases) when the training data's distribution gets slightly changed while the minimizer of the original training data ...
Sam's user avatar
  • 393
2 votes
1 answer

Uncertainty score from Monte Carlo dropout

When using a neural network for multi-class classification, there are situations where it is useful to estimate the uncertainty of the network's predicted class. One leading method for estimating ...
D.W.'s user avatar
  • 6,688
0 votes
0 answers

Splitting data to study datsets based on in- and out-of-distribution

I found an interesting paper for which they evaluate the in and outdistribution on different splittings of the dataset. For this they propose four different in distribution settings. The two I'm ...
user360952's user avatar
3 votes
0 answers

Random Forest vs Gradient Boosting out of distribution

I'm working on a classification task where I have data from a certain company for years between 2017 and 2020. Trying to train different models (Random Forest, XgBoost, LightGBM, Catboost, Explainable ...
Filippo Fedeli's user avatar
3 votes
2 answers

How to intuit the covariate shift?

Out of distribution and shifting data distribution are two types of dataset shift 1, I can understand what out-of-distribution means but not what shifting data distributions are. In that blog an ...
Lerner Zhang's user avatar
  • 6,728
4 votes
1 answer

Bayesian neural networks and out-of-distribution data?

In a Bayesian neural network (for classification) the posterior predictive distribution is $$ P(y=c \mid {\bf x}, \mathcal D_{train}) = \int P(y=c \mid {\bf x}, \theta) p(\theta \mid \mathcal D_{train}...
chris elgoog's user avatar