Divergent Angular Representation for Open Set Image Recognition

Park, Jaewoo; Low, Cheng Yaw; Teoh, Andrew Beng Jin

doi:10.1109/tip.2021.3128318

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the continuous development of deep learning, deep neural networks (DNNs) have achieved great success in various artificial intelligence fields, such as image recognition [1,2], natural language processing [3,4] and automatic driving [5,6], and other specific applications have shown significant advantages, especially recently applied to the Internet of Things [7,8], which greatly improves the efficiency of wireless communication transmission and the performance of resource allocation. However, DNNs are vulnerable to adversarial examples that misidentify the recognition results of DNNs by adding subtle perturbations to the normal examples, which means that applying deep neural networks in the field of artificial intelligence will have serious security problems [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Physical adversarial attack in artificial intelligence of things

Ma,

Yang,

Zhang

et al. 2023

IET Communications

View full text Add to dashboard Cite

With the continuous development of wireless communication and artificial intelligence technology, Internet of Things (IoT) technology has made great progress. Deep learning methods are currently used in IoT technology, but deep neural networks (DNNs) are notoriously susceptible to adversarial examples, and subtle pixel changes to images can result in incorrect recognition results from DNNs. In the real‐world application, the patches generated by the recent physical attack methods are larger or less realistic and easily detectable. To address this problem, a Generative Adversarial Network based on Visual attention model and Style transfer network (GAN‐VS) is proposed, which reduces the patch area and makes the patch more natural and less noticeable. A visual attention model combined with generative adversarial network is introduced to detect the critical regions of image recognition, and only generate patches within the critical regions to reduce patch area and improve attack efficiency. For any type of seed patch, an adversarial patch can be generated with a high degree of stylistic and content similarity to the attacked image by generative adversarial network and style transfer network. Experimental evaluation shows that the proposed GAN‐VS has good camouflage and outperforms state‐of‐the‐art adversarial patch attack methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Physical adversarial attack in artificial intelligence of things

Ma,

Yang,

Zhang

et al. 2023

IET Communications

View full text Add to dashboard Cite

show abstract

“…For example, studies [5][6][7] examining the susceptibility of downstream models to attacks have confirmed that transfer learning can protect these downstream models from being easily attacked, thereby enhancing their robustness. Due to its practicality, transfer learning has attracted extensive attention in the field of computer vision [8][9][10][11][12], and has been applied in many task scenarios such as transportation, medical treatment [13], social media [14] and art [15][16][17][18]. Various works [19] have been proposed to explore the problem of what and how to transfer from the pre-trained models.…”

Section: Introductionmentioning

confidence: 99%

Discrepant Semantic Diffusion Boosts Transfer Learning Robustness

Gao,

Bai,

Zhao

et al. 2023

Electronics

View full text Add to dashboard Cite

Transfer learning could improve the robustness and generalization of the model, reducing potential privacy and security risks. It operates by fine-tuning a pre-trained model on downstream datasets. This process not only enhances the model’s capacity to acquire generalizable features but also ensures an effective alignment between upstream and downstream knowledge domains. Transfer learning can effectively speed up the model convergence when adapting to novel tasks, thereby leading to the efficient conservation of both data and computational resources. However, existing methods often neglect the discrepant downstream–upstream connections. Instead, they rigidly preserve the upstream information without an adequate regularization of the downstream semantic discrepancy. Consequently, this results in weak generalization, issues with collapsed classification, and an overall inferior performance. The main reason lies in the collapsed downstream–upstream connection due to the mismatched semantic granularity. Therefore, we propose a discrepant semantic diffusion method for transfer learning, which could adjust the mismatched semantic granularity and alleviate the collapsed classification problem to improve the transfer learning performance. Specifically, the proposed framework consists of a Prior-Guided Diffusion for pre-training and a discrepant diffusion for fine-tuning. Firstly, the Prior-Guided Diffusion aims to empower the pre-trained model with the semantic-diffusion ability. This is achieved through a semantic prior, which consequently provides a more robust pre-trained model for downstream classification. Secondly, the discrepant diffusion focuses on encouraging semantic diffusion. Its design intends to avoid the unwanted semantic centralization, which often causes the collapsed classification. Furthermore, it is constrained by the semantic discrepancy, serving to elevate the downstream discrimination capabilities. Extensive experiments on eight prevalent downstream classification datasets confirm that our method can outperform a number of state-of-the-art approaches, especially for fine-grained datasets or datasets dissimilar to upstream data (e.g., 3.75% improvement for Cars dataset and 1.79% improvement for SUN dataset under the few-shot setting with 15% data). Furthermore, the experiments of data sparsity caused by privacy protection successfully validate our proposed method’s effectiveness in the field of artificial intelligence security.

show abstract

“…Additionally, some OSR methods aim at designing feature representations or classifiers with angles for improving interclass similarity and inter-class difference. Park et al [38] proposed to learn divergent angular representations, which improved the global directional feature variation. Cevikalp and Saglamlar [47] introduced a quasi-linear polyhedral conic classifier, which constrained the known-class regions to be L1 or L2 balls.…”

Section: B Inductive Methodsmentioning

confidence: 99%

A study on open set recognition methods

Sun¹

View full text Add to dashboard Cite

Ling Keck-Voon. He constantly encouraged and supported me throughout my Ph.D. career. He has helped me a lot in how to do academic research, in-depth thinking, and manuscript writing. I would like to thank Professor Lin Guoshen for his patient guidance and for leading me into the wonderful world of deep learning. Also, I would like to thank Nanyang Technological University, National Research Foundation Singapore, and SMRT Corporation for funding my education and research.

show abstract

Divergent Angular Representation for Open Set Image Recognition

Cited by 5 publications

References 30 publications

Physical adversarial attack in artificial intelligence of things

Physical adversarial attack in artificial intelligence of things

Discrepant Semantic Diffusion Boosts Transfer Learning Robustness

A study on open set recognition methods

Contact Info

Product

Resources

About