Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection

04/23/2022
by   Meng Xing, et al.
0

Out-of-distribution (OOD) detection is essential to handle the distribution shifts between training and test scenarios. For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution. In this paper, we propose a deep generative models (DGM) based transferable OOD detection method, which is unnecessary to retrain on a new ID dataset. We design an image erasing strategy to equip exclusive conditional entropy distribution for each ID dataset, which determines the discrepancy of DGM's posteriori ucertainty distribution on different ID datasets. Owing to the powerful representation capacity of convolutional neural networks, the proposed model trained on complex dataset can capture the above discrepancy between ID datasets without retraining and thus achieve transferable OOD detection. We validate the proposed method on five datasets and verity that ours achieves comparable performance to the state-of-the-art group based OOD detection methods that need to be retrained to deploy on new ID datasets. Our code is available at https://github.com/oOHCIOo/CETOOD.

READ FULL TEXT

page 8

page 9

research
03/25/2023

SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection

Building up reliable Out-of-Distribution (OOD) detectors is challenging,...
research
03/23/2023

Calibrated Out-of-Distribution Detection with a Generic Representation

Out-of-distribution detection is a common issue in deploying vision mode...
research
06/01/2023

In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation

Out-of-distribution (OOD) detection is the problem of identifying inputs...
research
09/12/2021

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...
research
11/17/2021

Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data

Deep network models perform excellently on In-Distribution (ID) data, bu...
research
06/06/2023

Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability

Out-of-distribution (OOD) detection is an indispensable aspect of secure...
research
07/28/2022

A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions

Modern deep neural network models are known to erroneously classify out-...

Please sign up or login with your details

Forgot password? Click here to reset