Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection

TL;DR

This paper introduces a Transformer-Encoder Detector Module that enhances object detection accuracy and robustness against adversarial attacks by incorporating contextual information, outperforming baseline models in various metrics.

Contribution

The paper presents a novel context module for object detectors that improves detection performance and adversarial robustness by integrating scene context and visual features.

Findings

Up to 13% higher mAP, F1, and AUC scores compared to baseline.

8-point higher mAP on adversarially attacked images.

Simple context module significantly enhances detector reliability.

Abstract

Deep neural network approaches have demonstrated high performance in object recognition (CNN) and detection (Faster-RCNN) tasks, but experiments have shown that such architectures are vulnerable to adversarial attacks (FFF, UAP): low amplitude perturbations, barely perceptible by the human eye, can lead to a drastic reduction in labeling performance. This article proposes a new context module, called \textit{Transformer-Encoder Detector Module}, that can be applied to an object detector to (i) improve the labeling of object instances; and (ii) improve the detector's robustness to adversarial attacks. The proposed model achieves higher mAP, F1 scores and AUC average score of up to 13\% compared to the baseline Faster-RCNN detector, and an mAP score 8 points higher on images subjected to FFF or UAP attacks due to the inclusion of both contextual and visual features extracted from scene and encoded into the model. The result demonstrates that a simple ad-hoc context module can improve the reliability of object detectors significantly.