کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6939821 870056 2017 10 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Learning scale-variant and scale-invariant features for deep image classification
ترجمه فارسی عنوان
ویژگی های مقیاس یادگیری و ویژگی های مقیاس غیر مجاز برای طبقه بندی تصویر عمیق
کلمات کلیدی
شبکه عصبی مصنوعی، چند مقیاس، نام مستعار هنرمند، ویژگی های مقیاس نوع،
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
Convolutional Neural Networks (CNNs) require large image corpora to be trained on classification tasks. The variation in image resolutions, sizes of objects and patterns depicted, and image scales, hampers CNN training and performance, because the task-relevant information varies over spatial scales. Previous work attempting to deal with such scale variations focused on encouraging scale-invariant CNN representations. However, scale-invariant representations are incomplete representations of images, because images contain scale-variant information as well. This paper addresses the combined development of scale-invariant and scale-variant representations. We propose a multi-scale CNN method to encourage the recognition of both types of features and evaluate it on a challenging image classification task involving task-relevant characteristics at multiple scales. The results show that our multi-scale CNN outperforms single-scale CNN. This leads to the conclusion that encouraging the combined development of a scale-invariant and scale-variant representation in CNNs is beneficial to image recognition performance.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 61, January 2017, Pages 583-592
نویسندگان
, ,