scholar.google.com › citations
We propose a robust object detection based on the contrastive learning perspective (RCP), which can learn features from both clean and adversarial samples.
In this paper, we propose an object detection/recognition al- gorithm based on a new set of shape-driven features and morphological operators. Each object class�...
People also ask
What is robust object detection?
What are the two main types of deep learning based object detection approaches?
What is the best model for object detection?
Is object detection machine learning or deep learning?
Dec 2, 2023 � We propose a uniform perspective object detection robustness model based on bilinear interpolation that can accurately identify clean and adversarial samples.
MTD [18] improves the robustness of object detectors against different types of attacks by generalizing the adversarial training framework from classification�...
We first revisit and systematically analyze object detectors and many recently developed attacks from the perspective of model robustness. We then present a�...
Oct 4, 2024 � On this basis, we propose a batch local comparison strategy with two BN branches to balance the detector's accuracy and robustness. Furthermore,�...
Missing: Perspective. | Show results with:Perspective.
Common domain adaptation approaches are based on ei- ther supervised model fine-tuning in the target domain or unsupervised cross-domain representation learning�...
Missing: Comparative | Show results with:Comparative
Robust Object Detection Based on a Comparative Learning Perspective � Hao Yang ... This work proposes a robust object detection based on the contrastive learning�...
This paper proposes a semi-supervised learning framework for object detection in autonomous vehicles, improving the robustness with unlabeled data.
Missing: Comparative | Show results with:Comparative
A Benchmark for the: Robustness of Object Detection Models to Image Corruptions and Distortions. To allow fair comparison of robustness enhancing methods�...
Missing: Comparative | Show results with:Comparative