Saliency for fine-grained object recognition in domains with scarce training data

Autor: Abel Gonzalez-Garcia, Carola Figueroa Flores, Joost van de Weijer, Bogdan Raducanu
Rok vydání: 2019
Předmět:
FOS: Computer and information sciences
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Pipeline (computing)
Feature extraction
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
01 natural sciences
Convolutional neural network
Image (mathematics)
Task (project management)
Artificial Intelligence
Salience (neuroscience)
0103 physical sciences
0202 electrical engineering
electronic engineering
information engineering
010306 general physics
Training set
business.industry
Process (computing)
Cognitive neuroscience of visual object recognition
Pattern recognition
Signal Processing
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
Zdroj: Pattern Recognition. 94:62-73
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2019.05.002
Popis: This paper investigates the role of saliency to improve the classification accuracy of a Convolutional Neural Network (CNN) for the case when scarce training data is available. Our approach consists in adding a saliency branch to an existing CNN architecture which is used to modulate the standard bottom-up visual features from the original image input, acting as an attentional mechanism that guides the feature extraction process. The main aim of the proposed approach is to enable the effective training of a fine-grained recognition model with limited training samples and to improve the performance on the task, thereby alleviating the need to annotate large dataset. % The vast majority of saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline. Our proposed pipeline allows to evaluate saliency methods for the high-level task of object recognition. We perform extensive experiments on various fine-grained datasets (Flowers, Birds, Cars, and Dogs) under different conditions and show that saliency can considerably improve the network's performance, especially for the case of scarce training data. Furthermore, our experiments show that saliency methods that obtain improved saliency maps (as measured by traditional saliency benchmarks) also translate to saliency methods that yield improved performance gains when applied in an object recognition pipeline.
Published in Pattern Recognition journal
Databáze: OpenAIRE
Externí odkaz: