Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection

TL;DR

This paper presents Situation Monitor, a zero-shot OOD detection method for transformer-based object detectors that improves accuracy, calibration, and efficiency using a diversity-driven budding ensemble architecture.

Contribution

It introduces the Diversity-based Budding Ensemble Architecture (DBEA) with a diversity loss, enhancing OOD detection and calibration in object detection models.

Findings

14% reduction in trainable parameters

Improved detection of Far-OOD samples

Enhanced confidence score calibration

Abstract

We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situation Monitor utilizes the Diversity-based Budding Ensemble Architecture (DBEA) and increases the OOD performance by integrating a diversity loss into the training process on top of the budding ensemble architecture, detecting Far-OOD samples and minimizing false positives on Near-OOD samples. Moreover, utilizing the resulting DBEA increases the model's OOD performance and improves the calibration of confidence scores, particularly concerning the intersection over union of the detected objects. The DBEA model achieves these advancements with a 14% reduction in trainable parameters compared to the vanilla model. This signifies a substantial improvement in efficiency without compromising the model's ability to detect OOD instances and calibrate the confidence scores accurately.