TTA-OOD: Test-time Augmentation for Improving Out-of-Distribution Detection in Gastrointestinal Vision

TL;DR

This paper introduces TTA-OOD, a test-time augmentation method that improves out-of-distribution detection in gastrointestinal endoscopic images by enhancing the distinction between healthy and abnormal cases.

Contribution

The paper proposes a novel test-time augmentation technique that enhances OOD detection in GI images, addressing data sparsity and rare condition challenges.

Findings

TTA-OOD improves OOD detection accuracy over baseline methods.

Test-time augmentation enhances semantic separation between ID and OOD examples.

The method outperforms existing state-of-the-art OOD scores in experiments.

Abstract

Deep learning has significantly advanced the field of gastrointestinal vision, enhancing disease diagnosis capabilities. One major challenge in automating diagnosis within gastrointestinal settings is the detection of abnormal cases in endoscopic images. Due to the sparsity of data, this process of distinguishing normal from abnormal cases has faced significant challenges, particularly with rare and unseen conditions. To address this issue, we frame abnormality detection as an out-of-distribution (OOD) detection problem. In this setup, a model trained on In-Distribution (ID) data, which represents a healthy GI tract, can accurately identify healthy cases, while abnormalities are detected as OOD, regardless of their class. We introduce a test-time augmentation segment into the OOD detection pipeline, which enhances the distinction between ID and OOD examples, thereby improving the effectiveness of existing OOD methods with the same model. This augmentation shifts the pixel space, which translates into a more distinct semantic representation for OOD examples compared to ID examples. We evaluated our method against existing state-of-the-art OOD scores, showing improvements with test-time augmentation over the baseline approach.