用于多光照图像异常检测的注意力融合逆向蒸馏
Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection
AI总结：
本文提出注意力融合逆向蒸馏（AFRD）方法，通过教师网络提取多光照图像特征并经注意力模块融合后由学生网络回归，以回归误差作为异常分数，在Eyecandies数据集上验证了其优于现有MLIAD方法。
摘要：
本研究针对多光照图像异常检测（MLIAD），其中利用多种光照条件来提升成像质量和异常检测性能。尽管已经提出了许多图像异常检测方法，但它们缺乏处理单一样本多个输入的能力，例如MLIAD中的多光照图像。因此，本研究提出了注意力融合逆向蒸馏（AFRD）来处理MLIAD中的多个输入。为此，AFRD利用预训练的教师网络从多个输入中提取特征。然后通过注意力模块将这些特征聚合成融合特征。随后，利用相应的学生网络对注意力融合特征进行回归。在推理过程中，回归误差被表示为异常分数。在Eyecandies上的实验表明，AFRD相比其他MLIAD替代方法取得了更优的MLIAD性能，同时也凸显了利用多种光照条件进行异常检测的优势。
英文摘要：
This study targets Multi-Lighting Image Anomaly Detection (MLIAD), where multiple lighting conditions are utilized to enhance imaging quality and anomaly detection performance. While numerous image anomaly detection methods have been proposed, they lack the capacity to handle multiple inputs for a single sample, like multi-lighting images in MLIAD. Hence, this study proposes Attention Fusion Reverse Distillation (AFRD) to handle multiple inputs in MLIAD. For this purpose, AFRD utilizes a pre-trained teacher network to extract features from multiple inputs. Then these features are aggregated into fused features through an attention module. Subsequently, a corresponding student net-work is utilized to regress the attention fused features. The regression errors are denoted as anomaly scores during inference. Experiments on Eyecandies demonstrates that AFRD achieves superior MLIAD performance than other MLIAD alternatives, also highlighting the benefit of using multiple lighting conditions for anomaly detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
