تقرير
XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
العنوان: | XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification |
---|---|
المؤلفون: | Berglind, Frej, Temam, Haron, Mukhopadhyay, Supratik, Das, Kamalika, Sajol, Md Saiful Islam, Kumar, Sricharan, Kallurupalli, Kumar |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition |
الوصف: | Detecting out-of-distribution (OOD) data at inference time is crucial for many applications of machine learning. We present XOOD: a novel extreme value-based OOD detection framework for image classification that consists of two algorithms. The first, XOOD-M, is completely unsupervised, while the second XOOD-L is self-supervised. Both algorithms rely on the signals captured by the extreme values of the data in the activation layers of the neural network in order to distinguish between in-distribution and OOD instances. We show experimentally that both XOOD-M and XOOD-L outperform state-of-the-art OOD detection methods on many benchmark data sets in both efficiency and accuracy, reducing false-positive rate (FPR95) by 50%, while improving the inferencing time by an order of magnitude. |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2208.00629 |
رقم الأكسشن: | edsarx.2208.00629 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!