Multi-Scale CNN for Fine-Grained Image Recognition

Most conventional fine-grained image recognitions are based on a two-stream model of object-level and part-level CNNs, where the part-level CNN is responsible for learning the object-parts and their spatial relationships. To train the part-level CNN, we first need to separate parts from an object. H...

Cijeli opis

Bibliografski detalji

Glavni autor:	Chee Sun Won
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2020-01-01
Serija:	IEEE Access
Teme:	Convolutional neural network (CNN) fine-grained image classification food recognition image resizing
Online pristup:	https://ieeexplore.ieee.org/document/9126789/
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!