Titlebook: Artificial Neural Networks and Machine Learning – ICANN 2021; 30th International C Igor Farkaš,Paolo Masulli,Stefan Wermter Conference proc

DAMN

(Input) Size Matters for CNN Classifiers that fully convolutional image classifiers are not agnostic to the input size but rather show significant differences in performance: presenting the same image at different scales can result in different outcomes. A closer look reveals that there is no simple relationship between input size and mod

frivolous

Accelerating Depthwise Separable Convolutions with Vector Processornted hardware accelerators are outstanding in terms of saving resources and energy. However, lightweight networks designed for small processors do not perform efficiently on these accelerators. Moreover, there are too many models to design an application-specific circuit for each model. In this work

Hyperlipidemia

隐语

Deep Unitary Convolutional Neural Networksignals either amplify or attenuate across the layers and become saturated. While other normalization methods aim to fix the stated problem, most of them have inference speed penalties in those applications that require running averages of the neural activations. Here we extend the unitary framework

步兵

GRIEF

上下倒置

,Meßvorrichtungen und Meßautomaten,ns to collect features from certain levels of the feature hierarchy, and do not consider the significant differences among them. We propose a better architecture of feature pyramid networks, named selective multi-scale learning (SMSL), to address this issue. SMSL is efficient and general, which can

esthetician

,Meßmikroskop und Profilprojektor,heir comparable results, most of these counting methods disregard the fact that crowd density varies enormously in the spatial and temporal domains of videos. This thus hinders the improvement in performance of video crowd counting. To overcome that issue, a new detection and regression estimation n

Decimate

https://doi.org/10.1007/978-3-322-96810-4vision problems in the most diverse areas. However, this type of approach requires a large number of samples of the problem to be treated, which often makes this type of approach difficult. In computer vision applications aimed at fruit growing, this problem is even more noticeable, as the performan

scrutiny