Fine-Grained Adversarial Semi-Supervised Learning

Mugnai, Daniele; Pernici, Federico; Turchini, Francesco; Bimbo, Alberto Del

doi:10.1145/3485473

Cited by 8 publications

(2 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the noise of pseudo-labels and improve the quality, Zou et al [51] use label regularization to filter labels with high confidence. To correct its own mistakes of pseudo-label, Mugnai et al [52] propose Gradient Reversal Layer (GRL) for fine-graining the labels. However, the main…”

Section: Self-supervised and Semi-supervised Learningmentioning

confidence: 99%

S$^{5}$Mars: Self-Supervised and Semi-Supervised Learning for Mars Segmentation

Zhang¹,

Lin²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning has become a powerful tool for Mars exploration. Mars terrain segmentation is an important Martian vision task, which is the base of rover autonomous planning and safe driving. However, existing deep-learning-based terrain segmentation methods face two problems: one is the lack of sufficient detailed and high-confidence annotations, and the other is the over-reliance of models on annotated training data. In this paper, we address these two problems from the perspective of joint data and method design. We first present a new Mars terrain segmentation dataset which contains 6K high-resolution images and is sparsely annotated based on confidence, ensuring the high quality of labels. Then to learn from this sparse data, we propose a representation-learning-based framework for Mars terrain segmentation, including a self-supervised learning stage (for pre-training) and a semi-supervised learning stage (for fine-tuning). Specifically, for self-supervised learning, we design a multi-task mechanism based on the masked image modeling (MIM) concept to emphasize the texture information of images. For semi-supervised learning, since our dataset is sparsely annotated, we encourage the model to excavate the information of unlabeled area in each image by generating and utilizing pseudo-labels online. We name our dataset and method Self-Supervised and Semi-Supervised Segmentation for Mars (S 5 Mars). Experimental results show that our method can outperform state-of-the-art approaches and improve terrain segmentation performance by a large margin. Our project is available at https://jhang2020.github.io/S5Mars.github.io/.

show abstract

Section: Self-supervised and Semi-supervised Learningmentioning

confidence: 99%

S$^{5}$Mars: Self-Supervised and Semi-Supervised Learning for Mars Segmentation

Zhang¹,

Lin²,

Fan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The study in [65] designs an SUL GeoNet to jointly estimate the monocular depth map on set of real-time image files. The authors of [47] use Semi-Supervised Learning to increase the quantity of training data available and to improve the performance of Fine-Grained Visual Categorization. Their approach employs unlabeled data and an adversarial optimization strategy in which a second-order pooling model is used to generate the internal feature representation.…”

Section: Real-time Approachesmentioning

confidence: 99%

SETTI: A S elf-supervised Adv E rsarial Malware De T ection Archi T ecture in an I oT Environment

Golmaryami

Taheri

Pooranian

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

In recent years, malware detection has become an active research topic in the area of Internet of Things (IoT) security. The principle is to exploit knowledge from large quantities of continuously generated malware. Existing algorithms practise available malware features for IoT devices and lack real-time prediction behaviours. More research is thus required on malware detection to cope with real-time misclassification of the input IoT data. Motivated by this, in this paper we propose an adversarial self-supervised architecture for detecting malware in IoT networks, SETTI, considering samples of IoT network traffic that may not be labeled. In the SETTI architecture, we design three self-supervised attack techniques, namely Self-MDS , GSelf-MDS and ASelf-MDS . The Self-MDS method considers the IoT input data and the adversarial sample generation in real-time. The GSelf-MDS builds a generative adversarial network model to generate adversarial samples in the self-supervised structure. Finally, ASelf-MDS utilizes three well-known perturbation sample techniques to develop adversarial malware and inject it over the self-supervised architecture. Also, we apply a defence method to mitigate these attacks, namely adversarial self-supervised training to protect the malware detection architecture against injecting the malicious samples. To validate the attack and defence algorithms, we conduct experiments on two recent IoT datasets: IoT23 and NBIoT. Comparison of the results shows that in the IoT23 dataset, the Self-MDS method has the most damaging consequences from the attacker’s point of view by reducing the accuracy rate from 98% to 74%. In the NBIoT dataset, the ASelf-MDS method is the most devastating algorithm that can plunge the accuracy rate from 98% to 77%.

show abstract

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-boosting Attention Mechanism

Shu

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Fine-Grained Adversarial Semi-Supervised Learning

Cited by 8 publications

References 86 publications

S$^{5}$Mars: Self-Supervised and Semi-Supervised Learning for Mars Segmentation

S$^{5}$Mars: Self-Supervised and Semi-Supervised Learning for Mars Segmentation

SETTI: A S elf-supervised Adv E rsarial Malware De T ection Archi T ecture in an I oT Environment

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-boosting Attention Mechanism

Contact Info

Product

Resources

About