A visual recognition system to process images includes a global sub-network including a convolutional layer and a first max pooling layer. A local sub-network is connected to receive data from the global sub-network, and includes at least two convolutional layers, each connected to a max pooling layer. A fusion network is connected to receive data from the local sub-network, and includes a plurality of fully connected layers that respectively determine local feature maps derived from images. A loss layer is connected to receive data from the fusion network, set filter parameters, and minimize ranking error.
POINT TO SET SIMILARITY COMPARISON AND DEEP FEATURE LEARNING FOR VISUAL RECOGNITION
VERGLEICH VON POINT-TO-SET-ÄHNLICHKEIT UND TIEFENFUNKTIONSLERNEN ZUR VISUELLEN ERKENNUNG
COMPARAISON DE SIMILARITÉS DE POINTS À UN ENSEMBLE ET APPRENTISSAGE PROFOND DE CARACTÉRISTIQUES PERMETTANT UNE RECONNAISSANCE VISUELLE
2020-09-30
Patent
Electronic Resource
English
IPC: | B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V |
POINT TO SET SIMILARITY COMPARISON AND DEEP FEATURE LEARNING FOR VISUAL RECOGNITION
European Patent Office | 2018
|POINT TO SET SIMILARITY COMPARISON AND DEEP FEATURE LEARNING FOR VISUAL RECOGNITION
European Patent Office | 2018
|Person-Similarity Weighted Feature for Expression Recognition
Springer Verlag | 2007
|Statistical adaptive metric learning in visual action feature set recognition
British Library Online Contents | 2016
|Statistical adaptive metric learning in visual action feature set recognition
British Library Online Contents | 2016
|