Файл:2016-04-30 MULTI-SCALE CONTEXT AGGREGATION BY Dilated Convolutions.pdf

Материал из Материалы по машинному обучению
Перейти к: навигация, поиск
2016-04-30_MULTI-SCALE_CONTEXT_AGGREGATION_BY_Dilated_Convolutions.pdf(0 × 0 пикселей, размер файла: 2,86 МБ, MIME-тип: application/pdf)

Fisher Yu Princeton University Vladlen Koltun Intel Labs

ABSTRACT

State-of-the-art models for semantic segmentation are based on adaptations of convolutional networks that had originally been designed for image classification. However, dense prediction problems such as semantic segmentation are structurally different from image classification. In this work, we develop a new convolutional network module that is specifically designed for dense prediction. The presented module uses dilated convolutions to systematically aggregate multiscale contextual information without losing resolution. The architecture is based on the fact that dilated convolutions support exponential expansion of the receptive field without loss of resolution or coverage. We show that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems. In addition, we examine the adaptation of image classification networks to dense prediction and show that simplifying the adapted network can increase accuracy.


Keywords: VGG-16 network, Conditional Random Fields as Recurrent Neural Networks (CRF-RNN), Fully Convolutional Network (FCN-8s), DeepLab network

История файла

Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.

Дата/времяРазмерыУчастникПримечание
текущий16:26, 22 декабря 20160 × 0 (2,86 МБ)Slikos (обсуждение | вклад)
  • Вы не можете перезаписать этот файл.

Следующая 1 страница ссылается на данный файл: