Yuanjian Zhang

Jinchegn Hu, Jihao Li, Zhuoran Hou et al.

The problem of robustness in adverse weather conditions is considered a significant challenge for computer vision algorithms in the applicants of autonomous driving. Image rain removal algorithms are a general solution to this problem. They find a deep connection between raindrops/rain-streaks and images by mining the hidden features and restoring information about the rain-free environment based on the powerful representation capabilities of neural networks. However, previous research has focused on architecture innovations and has yet to consider the vulnerability issues that already exist in neural networks. This research gap hints at a potential security threat geared toward the intelligent perception of autonomous driving in the rain. In this paper, we propose a universal rain-removal attack (URA) on the vulnerability of image rain-removal algorithms by generating a non-additive spatial perturbation that significantly reduces the similarity and image quality of scene restoration. Notably, this perturbation is difficult to recognise by humans and is also the same for different target images. Thus, URA could be considered a critical tool for the vulnerability detection of image rain-removal algorithms. It also could be developed as a real-world artificial intelligence attack method. Experimental results show that URA can reduce the scene repair capability by 39.5% and the image generation quality by 26.4%, targeting the state-of-the-art (SOTA) single-image rain-removal algorithms currently available.

Runhao Liu, Ziming Chen, Peng Zhang

Skin cancer classification remains a challenging problem due to high inter-class similarity, intra-class variability, and image noise in dermoscopic images. To address these issues, we propose an improved ResNet-50 model enhanced with Adaptive Spatial Feature Fusion (ASFF), which adaptively integrates multi-scale semantic and surface features to improve feature representation and reduce overfitting. The ResNet-50 model is enhanced with an adaptive feature fusion mechanism to achieve more effective multi-scale feature extraction and improve overall performance. Specifically, a dual-branch design fuses high-level semantic and mid-level detail features, which are processed through global average pooling and fully connected layers to generate adaptive weights for weighted fusion, thereby strengthening feature learning and reducing the impact of noise on classification. The method is evaluated on a subset of the ISIC 2020 dataset containing 3297 benign and malignant skin lesion images. Experimental results show that the proposed ASFF-based ResNet-50 achieves the best overall performance compared with 5 classic convolutional neural networks (CNNs) models. The proposed model reached an accuracy of 93.18% along with higher precision, recall, specificity, and F1 score. The improved model achieves an AUC value of 0.9670 and 0.9717 in the P-R and ROC curve, respectively. Then, the evaluation based on Grad-CAM further proved that the improved model adaptively focuses on lesion-relevant regions while suppressing irrelevant background information, thereby validating its enhanced feature learning capability from a deep representation perspective. These findings demonstrate that the proposed approach provides a more effective and efficient solution for computer-aided skin cancer diagnosis.