Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features

by   Ibrahima Ndiour, et al.

This paper presents a principled approach for detecting out-of-distribution (OOD) samples in deep neural networks (DNN). Modeling probability distributions on deep features has recently emerged as an effective, yet computationally cheap method to detect OOD samples in DNN. However, the features produced by a DNN at any given layer do not fully occupy the corresponding high-dimensional feature space. We apply linear statistical dimensionality reduction techniques and nonlinear manifold-learning techniques on the high-dimensional features in order to capture the true subspace spanned by the features. We hypothesize that such lower-dimensional feature embeddings can mitigate the curse of dimensionality, and enhance any feature-based method for more efficient and effective performance. In the context of uncertainty estimation and OOD, we show that the log-likelihood score obtained from the distributions learnt on this lower-dimensional subspace is more discriminative for OOD detection. We also show that the feature reconstruction error, which is the L_2-norm of the difference between the original feature and the pre-image of its embedding, is highly effective for OOD detection and in some cases superior to the log-likelihood scores. The benefits of our approach are demonstrated on image features by detecting OOD images, using popular DNN architectures on commonly used image datasets such as CIFAR10, CIFAR100, and SVHN.


page 1

page 2

page 3

page 4


Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection

This paper presents a fast, principled approach for detecting anomalous ...

Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

We present a principled approach for detecting out-of-distribution (OOD)...

FRE: A Fast Method For Anomaly Detection And Segmentation

This paper presents a fast and principled approach for solving the visua...

Dimensionality Reduction Flows

Deep generative modelling using flows has gained popularity owing to the...

Parameter Optimization using high-dimensional Bayesian Optimization

In this thesis, I explore the possibilities of conducting Bayesian optim...

Variational Saccading: Efficient Inference for Large Resolution Images

Image classification with deep neural networks is typically restricted t...

Online Categorical Subspace Learning for Sketching Big Data with Misses

With the scale of data growing every day, reducing the dimensionality (a...

Please sign up or login with your details

Forgot password? Click here to reset