Affine Disentangled GAN for Interpretable and Robust AV Perception
원문 초록
Autonomous vehicles (AV) have progressed rapidly with the advancements in computer vision algorithms. The deep convolutional neural network as the main contributor to this advancement has boosted the classification accuracy dramatically. However, the discovery of adversarial examples reveals the generalization gap between dataset and the real world. Furthermore, affine transformations may also confuse computer vision based object detectors. The degradation of the perception system is undesirable for safety critical systems such as autonomous vehicles. In this paper, a deep learning system is proposed: Affine Disentangled GAN (ADIS-GAN), which is robust against affine transformations and adversarial attacks. It is demonstrated that conventional data augmentation for affine transformation and adversarial attacks are orthogonal, while ADIS-GAN can handle both attacks at the same time. Useful information such as image rotation angle and scaling factor are also generated in ADIS-GAN. On MNIST dataset, ADIS-GAN can achieve over 98 percent classification accuracy within 30 degrees rotation, and over 90 percent classification accuracy against FGSM and PGD adversarial attack.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation
Augmentation Techniques Analysis with Removal of Class Imbalance Using PyTorch for Intel Scene Dataset
Discrete Wavelet Transform for Generative Adversarial Network to Identify Drivers Using Gyroscope and Accelerometer Sensors
DocXClassifier: High Performance Explainable Deep Network for Document Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.