Anomaly detection is important in many real-life applications. Recently, self-supervised learning has greatly helped deep anomaly detection by recognizing several geometric transformations. However these methods lack finer features, usually highly depend on the anomaly type, and do not perform well on fine-grained problems. To address these issues, we first introduce in this work three novel and efficient discriminative and generative tasks which have complementary strength: (i) a piece-wise jigsaw puzzle task focuses on structure cues; (ii) a tint rotation recognition is used within each piece, taking into account the colorimetry information; (iii) and a partial re-colorization task considers the image texture. In order to make the re-colorization task more object-oriented than background-oriented, we propose to include the contextual color information of the image border via an attention mechanism. We then present a new out-of-distribution detection function and highlight its better stability compared to existing methods. Along with it, we also experiment different score fusion functions. Finally, we evaluate our method on an extensive protocol composed of various anomaly types, from object anomalies, style anomalies with fine-grained classification to local anomalies with face anti-spoofing datasets. Our model significantly outperforms state-of-the-art with up to 36% relative error improvement on object anomalies and 40% on face anti-spoofing problems.
翻译:在许多现实应用中,异常的检测非常重要。 最近, 自我监督的学习通过识别几何转换, 极大地帮助了深层次异常现象的检测。 但是, 这些方法缺乏精细的特征, 通常高度依赖异常类型, 并且没有很好地处理细细细的问题。 为了解决这些问题, 我们首先在这项工作中引入三种新颖而高效的区别性和基因化任务, 具有互补的力度:(一) 以结构提示为焦点的拼图拼图拼图任务;(二) 每种作品中都使用色调识别, 同时考虑到色度信息;(三) 部分重新颜色化任务考虑图像纹理。 为了让重新颜色化任务更面向目标而非背景, 我们提议通过关注机制将图像边框的背景颜色信息包含在内。 然后我们提出一个新的分配外检测功能, 并突出它与现有方法相比的稳定性。 同时, 我们还试验不同的40组合功能。 最后, 我们评估了由各种异常对象类型组成的广泛协议的方法, 从对象异常类型, 从对象异常, 风格的风格, 我们的风格, 我们的异常性, 我们的风格, 与精确的变形的变型, 我们的变型, 我们的变型, 与精确的变型的变型, 我们的变型, 我们的变型, 的, 的, 的 的 的, 的, 的, 我们的, 与精确的, 等式的变式的, 我们的, 我们的, 的, 的, 的, 的, 我们的, 的, 的, 的, 的, 的, 等式的, 我们的, 等的, 等的, 的, 等的, 等的, 等式的, 等的, 等的, 等的, 等的, 等的, 等的, 等的, 等的, 等的, 等的, 等的, 等式的, 等式的, 等的, 等式的, 等式的, 等的, 等式的, 等式的, 等的, 等式的, 等式的, 等式的, 等式, 等式的, 等式的, 等式的, 等式的, 等式的,