Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best peforming approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose PatchCore, which uses a maximally representative memory bank of nominal patchfeatures. PatchCore offers competitive inference times while achieving state-of-the-art performance for both detection and localization. On the standard dataset MVTec AD Patch-Core achieves an image-level anomaly detection AUROC score of 99.1%, more than halving the error compared to the next best competitor. We further report competitive results on two additional datasets and also find competitive results in the few samples regime. * Work done during an internship at Amazon Tübingen.1 Commonly also dubbed one-class classification (OCC).
We introduce SUBIC, a supervised structured binary code (concatenation of one-hot blocks). It is produced by a novel supervised deep convolutional network and is well adapted to efficient visual search, including category retrieval for which it outperforms the state-of-the-art supervised deep binary hashing techniques.
AbstractFor large-scale visual search, highly compressed yet meaningful representations of images are essential. Structured vector quantizers based on product quantization and its variants are usually employed to achieve such compression while minimizing the loss of accuracy. Yet, unlike binary hashing schemes, these unsupervised methods have not yet benefited from the supervision, end-to-end learning and novel architectures ushered in by the deep learning revolution. We hence propose herein a novel method to make deep convolutional neural networks produce supervised, compact, structured binary codes for visual search. Our method makes use of a novel block-softmax nonlinearity and of batch-based entropy losses that together induce structure in the learned encodings. We show that our method outperforms state-of-the-art compact representations based on deep hashing or structured quantization in single and cross-domain category retrieval, instance retrieval and classification. We make our code and models publicly available online.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.