Mar 11, 2024 · In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models.
scholar.google.com › citations
In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient ...
In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient ...
Mar 15, 2024 · Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be ...
Adversarial training has been validated in image compression models as a common method to enhance model robustness. Backdoor Attack · Image Compression +1.
Mar 5, 2024 · This paper proposes the attention information bottleneck-guided knowledge distillation (AIB-KD) method to enhance models' adversarial robustness.
Adversarial training has been validated in image compression models as a common method to enhance model robustness. Backdoor Attack · Image Compression +1.
This specially designed, robust distillation technique utilizes prior knowledge obtained from a robust pre-trained model to boost information bottlenecks ...
This work develops a framework to investigate the key issues relate the most to training robust and lightweight models.
The proposed method exhibits better adversarial robustness than current defense techniques in feature fusion based automatic modulation classification models in ...