Image copy detection and retrieval from large databases leverage two components. First, a neural network maps an image to a vector representation, that is relatively robust to various transformations of the image. Second, an efficient but approximate similarity search algorithm trades scalability (size and speed) against quality of the search, thereby introducing a source of error. This paper improves the robustness of image copy detection with active indexing, that optimizes the interplay of these two components. We reduce the quantization loss of a given image representation by making imperceptible changes to the image before its release. The loss is back-propagated through the deep neural network back to the image, under perceptual constraints. These modifications make the image more retrievable. Our experiments show that the retrieval and copy detection of activated images is significantly improved. For instance, activation improves by $+40\%$ the Recall1@1 on various image transformations, and for several popular indexing structures based on product quantization and locality sensitivity hashing.
翻译:首先,神经网络将图像映射成矢量表示,相对地与图像的各种变异相对可靠。 其次,高效但近似相似的搜索算法根据搜索质量进行缩放(大小和速度),从而引入一个错误源。 本文用主动索引化来提高图像复制检测的稳健性, 从而优化这两个元件的相互作用。 我们通过在图像发布前对图像进行无法辨别的修改, 减少给定图像表示的四分制损失。 损失通过深神经网络回溯到图像, 受感知性限制。 这些修改使图像更容易检索。 我们的实验显示, 激活图像的检索和复制检测得到显著改善。 例如, 激活了 $+40$ 的图像转换, 以及基于产品定量化和地点敏感度的几种流行索引结构 。