Proceedings ArticleDOI
Uncertainty-Aware Data Augmentation for Food Recognition
Eduardo Aguilar,Bhalaji Nagarajan,Rupali Khantun,Marc Bolaños,Petia Radeva +4 more
- pp 4017-4024
Reads0
Chats0
TLDR
In this article, a data augmentation strategy that estimates and uses the epistemic uncertainty to guide the model training is proposed, where the new synthetic images are generated from the hard to classify real ones present in the training data.Abstract:
Food recognition has recently attracted attention of many researchers. However, high food ambiguity, inter-class variability and intra-class similarity define a real challenge for the Deep learning and Computer Vision algorithms. In order to improve their performance, it is necessary to better understand what the model learns and, from this, to determine the type of data that should be additionally included for being the most beneficial to the training procedure. In this paper, we propose a new data augmentation strategy that estimates and uses the epistemic uncertainty to guide the model training. The method follows an active learning framework, where the new synthetic images are generated from the hard to classify real ones present in the training data based on the epistemic uncertainty. Hence, it allows the food recognition algorithm to focus on difficult images in order to learn their discriminatives features. On the other hand, avoiding data generation from images that do not contribute to the recognition makes it faster and more efficient. We show that the proposed method allows to improve food recognition and provides a better trade-off between micro- and macro-recall measures.read more
Citations
More filters
Posted Content
A Comprehensive Survey of Image-Based Food Recognition and Volume Estimation Methods for Dietary Assessment
Ghalib Ahmed Tahir,Chu Kiong Loo +1 more
TL;DR: In this article, a survey of visual-based methods for food recognition and volume estimation is presented, discussion and evaluation of these methods on popular food image databases and the mobile applications that are implementing these methods.
Journal ArticleDOI
A Mobile Food Recognition System for Dietary Assessment
TL;DR: Developing a mobile friendly, Middle Eastern cuisine focused food recognition application for assisted living purposes using the Mobilenet-v2 deep learning model, which achieves 94% accuracy on 23 food classes and has potential to serve the visually impaired in automatic food recognition via images.
Journal ArticleDOI
Applying deep learning image recognition technology to promote environmentally sustainable behavior
TL;DR: In this paper , a carbon footprint tracking system using convolutional neural network image recognition technology was proposed to explore and improve the advantages of environmentally sustainable eating behavior, and the accuracy of the proposed model is 94.79%, indicating it can effectively recognize food types.
Book ChapterDOI
A Mobile Food Recognition System for Dietary Assessment
TL;DR: In this article , a mobile friendly, Middle Eastern cuisine focused food recognition application for assisted living purposes was developed, which utilizes the Mobilenet-v2 deep learning model for low-latency, high-accuracy food classification.
Posted Content
A Review of the Vision-based Approaches for Dietary Assessment.
Ghalib Ahmed Tahir,Chu Kiong Loo +1 more
TL;DR: A review of visual-based methods for food recognition can be found in this article, which discusses the most performing methodologies that have been developed so far for automatic food recognition and discusses the mobile applications that are implementing these methods.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Journal ArticleDOI
SMOTE: synthetic minority over-sampling technique
TL;DR: In this article, a method of over-sampling the minority class involves creating synthetic minority class examples, which is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
Proceedings ArticleDOI
Rethinking the Inception Architecture for Computer Vision
TL;DR: In this article, the authors explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Journal ArticleDOI
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
TL;DR: This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.