Let’s Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving

Uřičář, Michal; Sistu, Ganesh; Rashed, Hazem; Vobecký, Antonín; Kumar, Varun; Křížek, Pavel; Bürger, Fabian; Yogamani, Senthil

doi:10.1109/wacv48630.2021.00081

Cited by 29 publications

(22 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GAN-guided strategy, requiring rare separate GAN network rendering occlusion traits, is subsequently evaluated in Sec. 4.3 on dirt disentanglement, relying on the recent DirtyGAN [81]. The experiments are all evaluated on a qualitative and quantitative basis, relying on GAN metrics as well as proxy tasks.…”

Section: Methodsmentioning

confidence: 99%

“…We later describe models used for disentanglement. DirtyGAN [81] Table 1: Disentanglement tasks. For each task, we indicate the features entangled in the target domain (also, shorten as indices of task name), the datasets, and the model or GAN guidance employed for disentanglement.…”

Section: Tasksmentioning

confidence: 99%

“…For guidance, we exploit DirtyGAN [81], a GAN-based framework for opaque soiling occlusion generation. It is composed by two components, i.e.…”

Section: Guidancementioning

confidence: 99%

“…To train DirtyGAN, we first train a VAE to learn the shape of soiling, and then proceed to train a modified CycleGAN [96] to generate realistic soiling, conditioning the soiling shape on the VAE outputs. For more details on this we refer to [81].…”

Section: Guidancementioning

confidence: 99%

“…Following the GAN-guided pipeline (Fig. 2), DirtyGAN [81] is trained beforehand and frozen during the disentanglement.…”

Section: Disentanglement Evaluationmentioning

confidence: 99%

See 4 more Smart Citations

Physics-informed Guided Disentanglement in Generative Networks

Pizzati¹,

Cerri²,

Charette³

2021

Preprint

View full text Add to dashboard Cite

Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), thus lowering the translation quality and variability. In this paper, we present a comprehensive method for disentangling physics-based traits in the translation, guiding the learning process with neural or physical models. For the latter, we integrate adversarial estimation and genetic algorithms to correctly achieve disentanglement. The results show our approach dramatically increase performances in many challenging scenarios for image translation. Keywords Adversarial learning • image to image translation • feature disentanglement • adverse weather • vision and rain • GAN

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Tasksmentioning

confidence: 99%

“…For guidance, we exploit DirtyGAN [81], a GAN-based framework for opaque soiling occlusion generation. It is composed by two components, i.e.…”

Section: Guidancementioning

confidence: 99%

Section: Guidancementioning

confidence: 99%

“…Following the GAN-guided pipeline (Fig. 2), DirtyGAN [81] is trained beforehand and frozen during the disentanglement.…”

Section: Disentanglement Evaluationmentioning

confidence: 99%

See 3 more Smart Citations

Physics-informed Guided Disentanglement in Generative Networks

Pizzati¹,

Cerri²,

Charette³

2021

Preprint

View full text Add to dashboard Cite

show abstract

MUDROID: Android malware detection and classification based on permission and behavior for autonomous vehicles

Tang,

Da,

Wang

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

With the growing popularity of autonomous vehicles, ensuring their safety has become a significant concern. Vehicle manufacturers have incorporated the Android operating system to enhance user convenience. However, the Android operating system's diversity and vulnerability may significantly impact autonomous vehicles because these natures lead to a critical threat in autonomous vehicle security: Android malware. The complex nature of multi‐data sources fusion in autonomous driving systems has resulted in low detection efficiency and accuracy for Android malware. Given the security requirements for autonomous‐driving systems, this article presents an Android malware classification method centered around the multifeature fusion and deep learning architecture designed to detect and classify Android malware within autonomous‐driving systems. The proposed MUDROID framework relies on the Android permission mechanism and behavioral feature to formulate a malware classification model. Comprising four essential components—feature extraction, representation, multifeature fusion, and classifier training, MUDROID leverages the advantages of CNN and GCN combination model and is adept at extracting and interpreting multidimensional features, consequently constructing a multifeature fusion classifier to amplify the efficiency and accuracy of Android malware detection and classification. The experiment results support MUDROID's superior classification performance, with an impressive Android malware detection accuracy rate of 98.69% and family classification (95.42%). The proposed method can detect and classify Android malware effectively, thus elevating the security and robustness of the self‐driving system. Additionally, the approach in this article also addresses feature representation issues in detecting malware variants, facilitating the recognition of Android malware variants across diverse platforms.

show abstract