提出增量降维方法，高效处理海量图像异常检测。
Incremental dimension reduction for efficient and accurate visual anomaly detection
- 分批处理特征，逐步更新奇异值和向量，降低内存占用。
- 在保持接近现有算法精度的前提下，显著加速训练过程。
- 适合大规模图像异常检测场景，尤其对资源受限系统友好。
当前视觉异常检测算法虽使用深度神经网络提取图像显著特征，但高维特征难以应用于包含数千张图像的大规模数据。为此，本文提出一种增量降维算法，对提取的特征进行压缩。该算法本质上计算特征的截断奇异值分解，但不同于一次性处理所有向量，而是将向量分批处理。每批更新已访问向量的截断奇异值与奇异向量，并用自身奇异值与向量对本批特征进行降维，实现低内存开销存储。全部批次处理完毕后，将各批的奇异向量重新映射至所有特征共有的奇异向量空间。实验表明，该方法可在保持接近先进异常检测算法精度的同时，显著加速训练过程。
原文摘要 · Abstract (English)
While nowadays visual anomaly detection algorithms use deep neural networks to extract salient features from images, the high dimensionality of extracted features makes it difficult to apply those algorithms to large data with 1000s of images. To address this issue, we present an incremental dimension reduction algorithm to reduce the extracted features. While our algorithm essentially computes truncated singular value decomposition of these features, other than processing all vectors at once, our algorithm groups the vectors into batches. At each batch, our algorithm updates the truncated singular values and vectors that represent all visited vectors, and reduces each batch by its own singular values and vectors so they can be stored in the memory with low overhead. After processing all batches, we re-transform these batch-wise singular vectors to the space spanned by the singular vectors of all features. We show that our algorithm can accelerate the training of state-of-the-art anomaly detection algorithm with close accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。