Bridging In- and Out-of-distribution Samples for Their Better Discriminability

by   Engkarat Techapanurak, et al.

This paper proposes a method for OOD detection. Questioning the premise of previous studies that ID and OOD samples are separated distinctly, we consider samples lying in the intermediate of the two and use them for training a network. We generate such samples using multiple image transformations that corrupt inputs in various ways and with different severity levels. We estimate where the generated samples by a single image transformation lie between ID and OOD using a network trained on clean ID samples. To be specific, we make the network classify the generated samples and calculate their mean classification accuracy, using which we create a soft target label for them. We train the same network from scratch using the original ID samples and the generated samples with the soft labels created for them. We detect OOD samples by thresholding the entropy of the predicted softmax probability. The experimental results show that our method outperforms the previous state-of-the-art in the standard benchmark tests. We also analyze the effect of the number and particular combinations of image corrupting transformations on the performance.



There are no comments yet.


page 3


Multi-pseudo Regularized Label for Generated Samples in Person Re-Identification

Sufficient training data is normally required to train deeply learned mo...

Revealing Distributional Vulnerability of Explicit Discriminators by Implicit Generators

An explicit discriminator trained on observable in-distribution (ID) sam...

Out of distribution detection for skin and malaria images

Deep neural networks have shown promising results in disease detection a...

A Uniform Framework for Anomaly Detection in Deep Neural Networks

Deep neural networks (DNN) can achieve high performance when applied to ...

Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy

Since deep learning models have been implemented in many commercial appl...

pseudo-Bayesian Neural Networks for detecting Out of Distribution Inputs

Conventional Bayesian Neural Networks (BNNs) are known to be capable of ...

No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets

Out-of-distribution detection is an important component of reliable ML s...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.