paper-with-me

Papers

Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions

2024-03-23 · Kaiwen Wang, Yinzhe Shen, Martin Lauer

Existing object detectors encounter challenges in handling domain shifts between training and real-world data, particularly under poor visibility conditions like fog and night. Cutting-edge cross-domain object detection methods use teacher-student frameworks and compel teacher and student models to produce consistent predictions under weak and strong augmentations, respectively. In this paper, we reveal that manually crafted augmentations are insufficient for optimal teaching and present a simple yet effective framework named Adversarial Defense Teacher (ADT), leveraging adversarial defense to enhance teaching quality. Specifically, we employ adversarial attacks, encouraging the model to generalize on subtly perturbed inputs that effectively deceive the model. To address small objects under poor visibility conditions, we propose a Zoom-in Zoom-out strategy, which zooms-in images for better pseudo-labels and zooms-out images and pseudo-labels to learn refined features. Our results demonstrate that ADT achieves superior performance, reaching 54.5% mAP on Foggy Cityscapes, surpassing the previous state-of-the-art by 2.6% mAP.

📄 PDF Abstract BibTeX arXiv:2403.15786

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Defenseobject-detectionObject Detection

Similar Papers 제목 키워드 기반

CIARD: Cyclic Iterative Adversarial Robustness Distillation

2025-09-16 · Liming Lu, Shuchao Pang, Xu Zheng, Xiang Gu 외 arxiv

Adversarial robustness distillation (ARD) aims to transfer both performance and robustness from teacher model to lightweight student model, enabling resilient performance on resource-constrained scenarios. Though existin…

Adversarial RobustnessAdversarial Defense

Distilling Adversarial Robustness Using Heterogeneous Teachers

2024-02-23 · Jieren Deng, Aaron Palmer, Rigel Mahmood, Ethan Rathbun 외

Achieving resiliency against adversarial attacks is necessary prior to deploying neural network classifiers in domains where misclassification incurs substantial costs, e.g., self-driving cars or medical imaging. Recent …

Adversarial RobustnessKnowledge DistillationSelf-Driving Cars

Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples

2024-03-08 · Eda Yilmaz, Hacer Yalim Keles

We introduce Adversarial Sparse Teacher (AST), a robust defense method against distillation-based model stealing attacks. Our approach trains a teacher model using adversarial examples to produce sparse logit responses a…

Knowledge Distillation

Cross-Domain Adaptive Teacher for Object Detection

2021-11-25 · CVPR 2022 1 · Yu-Jhe Li, Xiaoliang Dai, Chih-Yao Ma, Yen-Cheng Liu 외

We address the task of domain adaptation in object detection, where there is a domain gap between a domain with annotations (source) and a domain of interest without annotations (target). As an effective semi-supervised …

Data AugmentationDomain AdaptationObjectobject-detection+1

Adversarial Attacked Teacher for Unsupervised Domain Adaptive Object Detection

2024-08-18 · Kaiwen Wang, Yinzhe Shen, Martin Lauer

Object detectors encounter challenges in handling domain shifts. Cutting-edge domain adaptive object detection methods use the teacher-student framework and domain adversarial learning to generate domain-invariant pseudo…

object-detectionObject DetectionPseudo Label