Towards Total Recall in Industrial Anomaly Detection

We develop PatchCore - an anomaly detection method for visual product inspection, which is scalable, fast, extremely accurate, interpretable and usable without expert knowledge. Using Coreset Memories, PatchCore has retained the state-of-the-art for more than a year now.

Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schoelkopf, Thomas Brox, Peter Gehler

CVPR, 2022

arXiv | code

Lowshot Visual Recognition

To solve the lowshot visual recognition problem, we use a related dataset with sufficient number of samples per class to learn representations using a Convolutional Neural Network (CNN). This CNN is used to extract features of the lowshot samples and learn a classifer . During representation learning, we enforce the learnt representations to obey certain property by using a custom loss function. We believe that when the lowshot samples obey this property the classifcation step becomes easier. We show that the proposed solution performs better than the softmax classifer by a good margin.

Masters thesis, Virginia Tech, 2022

Thesis

We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. Using this architecture we are able to outperform our prior results in accuracy vs signal to noise ratio against an identical system without attention, however we believe such an attention model has implication far beyond the task of modulation recognition

ASILOMAR, 2016

paper