Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models

Qutub Syed, Michael Paulitsch, Karthik Pattabiraman, Korbinian Hagn, Fabian Oboril, Cornelius Buerkle, Kay Ulrich Scholl, Gereon Hinz, Alois Knoll

Research output: Contribution to journalConference articlepeer-review

Abstract

As transformer-based object detection models progress, their impact in critical sectors like autonomous vehicles and aviation is expected to grow. Soft errors causing bit flips during inference have significantly impacted DNN performance, altering predictions. Traditional range restriction solutions for CNNs fall short for transformers. This study introduces the Global Clipper and Global Hybrid Clipper, effective mitigation strategies specifically designed for transformer-based models. It significantly enhances their resilience to soft errors and reduces faulty inferences to 0%. We also detail extensive testing across over 64 scenarios involving two transformer models (DINO-DETR and Lite-DETR) and two CNN models (YOLOv3 and SSD) using three datasets, totalling approximately 3.3 million inferences, to assess model robustness comprehensively. Moreover, the paper explores unique aspects of attention blocks in transformers and their operational differences from CNNs.

Original languageEnglish
JournalCEUR Workshop Proceedings
Volume3856
StatePublished - 2024
Event2024 IJCAI Workshop on Artificial Intelligence Safety, AISafety 2024 - Jeju, Korea, Republic of
Duration: 4 Aug 2024 → …

Fingerprint

Dive into the research topics of 'Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models'. Together they form a unique fingerprint.

Cite this