Semantic-aware scene recognition
Entidad
UAM. Departamento de Tecnología Electrónica y de las ComunicacionesEditor
ElsevierFecha de edición
2020-06-01Cita
10.1016/j.patcog.2020.107256
López-Cifuentes, A.; Escudero-Viñolo, M.; Bescós, J.; García-Martín, Á. (2020) Semantic-aware scene recognition, 152, 107256.
ISSN
0031-3203DOI
10.1016/j.patcog.2020.107256Financiado por
This study has been partially supported by the Spanish Government through its TEC2017-88169-R MobiNetVideo projectProyecto
Gobierno de España. TEC2017-88169-RVersión del editor
https://doi.org/10.1016/j.patcog.2020.107256Materias
Convolutional neural networks; Deep learning; Scene recognition; Semantic segmentation; TelecomunicacionesDerechos
© 2020 Elsevier Ltd.
Esta obra está bajo una licencia de Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 Internacional.
Resumen
Scene recognition is currently one of the top-challenging research fields in computer vision. This may be due to the ambiguity between classes: images of several scene classes may share similar objects, which causes confusion among them. The problem is aggravated when images of a particular scene class are notably different. Convolutional Neural Networks (CNNs) have significantly boosted performance in scene recognition, albeit it is still far below from other recognition tasks (e.g., object or image recognition). In this paper, we describe a novel approach for scene recognition based on an end-to-end multi-modal CNN that combines image and context information by means of an attention module. Context information, in the shape of a semantic segmentation, is used to gate features extracted from the RGB image by leveraging on information encoded in the semantic representation: the set of scene objects and stuff, and their relative locations. This gating process reinforces the learning of indicative scene content and enhances scene disambiguation by refocusing the receptive fields of the CNN towards them. Experimental results on three publicly available datasets show that the proposed approach outperforms every other state-of-the-art method while significantly reducing the number of network parameters. All the code and data used along this paper is available at: https://github.com/vpulab/Semantic-Aware-Scene-Recognition
Lista de ficheros
Google Scholar:López Cifuentes, Alejandro
-
Escudero Viñolo, Marcos
-
Bescos Cano, Jesús
-
García Martín, Álvaro
Lista de colecciones del ítem
Registros relacionados
Mostrando ítems relacionados por título, autor, creador y materia.