Learning to Make Better Mistakes

Wu, Hui; Merler, Michele; Uceda-Sosa, Rosario; Smith, J. R.

doi:10.1145/2964284.2967205

Cited by 55 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are various popular CNN architectures for image processing including AlexNet (Krizhevsky et al, 2012), a network using repetitive units called visual geometry group network (VGG) (Simonyan & Zisserman, 2014), GoogLeNet (Szegedy et al, 2015) that includes parallel data channels, and residual neural network (ResNet) (He, Zhang, Ren, & Sun, 2016) constructed by residual (Heravi, Aghdam, & Puig, 2018) 65.40 87.00 CNN-FOOD 70.41 / Multitask (H. Wu, Merler, Uceda-Sosa, & Smith, 2016) 72.11 / FoodNet (Pandey, Deepthi, Mandal, & Puhan, 2017) 72.12 91.61 DeepFood (Liu et al, 2016a) 77.40 93.70 Inception Module (C. 77.00 94.00 ResNet (Fu et al, 2017) 78.50 94.10 ResNet-50 (Ciocca, Napoletano, & Schettini, 2018) 82.54 95.79 Inception-v3+FPCNN (Zheng, Zou, & Wang, 2018) 87.96 / Inception V3 (Hassannejad et al, 2016) 88.28 96.88 wide-slice residual networks (WISeR) (Martinel, Foresti, & Micheloni, 2018) 90.27 98.71…”

Section: Deep Learning Applications In Food Food Recognition and Clasmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

Deep learning has been proved to be an advanced technology for big data analysis with a large number of successful cases in image processing, speech recognition, object detection, and so on. Recently, it has also been introduced in food science and engineering. To our knowledge, this review is the first in the food domain. In this paper, we provided a brief introduction of deep learning and detailedly described the structure of some popular architectures of deep neural networks and the approaches for training a model. We surveyed dozens of articles that used deep learning as the data analysis tool to solve the problems and challenges in food domain, including food recognition, calories estimation, quality detection of fruits, vegetables, meat and aquatic products, food supply chain, and food contamination. The specific problems, the datasets, the preprocessing methods, the networks and frameworks used, the performance achieved, and the comparison with other popular solutions of each research were investigated. We also analyzed the potential of deep learning to be used as an advanced data mining tool in food sensory and consume researches. The result of our survey indicates that deep learning outperforms other methods such as manual feature extractors, conventional machine learning algorithms, and deep learning as a promising tool in food quality and safety inspection. The encouraging results in classification and regression problems achieved by deep learning will attract more research efforts to apply deep learning into the field of food in the future.

show abstract

Section: Deep Learning Applications In Food Food Recognition and Clasmentioning

confidence: 99%

Application of Deep Learning in Food: A Review

Zhou

Zhang

Liu

et al. 2019

Comp Rev Food Sci Food Safe

388

166

View full text Add to dashboard Cite

show abstract

“…Most existing deep learning based work leverage off-theshelf models [11], [27]- [29] and train on static food image datasets [9], [12], [13], [30]- [32]. In order to address the issue of inter-class similarity and intra-class variability, a manually built hierarchy based food recognition is proposed in [10]. Later, Mao et al [9] propose to construct a food hierarchy based on visual similarity and nutrition content [33] without requiring human efforts.…”

Section: A Food Recognitionmentioning

confidence: 99%

“…As the first and fundamental step of image-based dietary assessment, food recognition aims to identify food types given an input image and the overall dietary assessment performance greatly relies on the precise food recognition results. Though existing deep learning based food recognition methods [5]- [10] have achieved remarkable performance by training off-the-shelf Convolutional Neural Networks (e.g. ResNet [11]) using static datasets (e.g.…”

Section: Introductionmentioning

confidence: 99%

Online Continual Learning For Visual Food Classification

Zhu

2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Deep learning based food recognition has achieved remarkable progress in predicting food types given an eating occasion image. However, there are two major obstacles that hinder deployment in real world scenario. First, as new foods appear sequentially overtime, a trained model needs to learn the new classes continuously without causing catastrophic forgetting for already learned knowledge of existing food types. Second, the distribution of food images in real life is usually long-tailed as a small number of popular food types are consumed more frequently than others, which can vary in different populations. This requires the food recognition method to learn from classimbalanced data by improving the generalization ability on instance-rare food classes. In this work, we focus on long-tailed continual learning and aim to address both aforementioned challenges. As existing long-tailed food image datasets only consider healthy people population, we introduce two new benchmark food image datasets, VFN-INSULIN and VFN-T2D, which exhibits on the real world food consumption for insulin takers and individuals with type 2 diabetes without taking insulin, respectively. We propose a novel end-to-end framework for long-tailed continual learning, which effectively addresses the catastrophic forgetting by applying an additional predictor for knowledge distillation to avoid misalignment of representation during continual learning. We also introduce a novel data augmentation technique by integrating class-activation-map (CAM) and CutMix, which significantly improves the generalization ability for instancerare food classes to address the class-imbalance issue. The proposed method is evaluated on Food101-LT, VFN-LT, VFN-INSULIN and VFN-T2D and show promising performance with large margin improvements compared with existing methods. We conduct an ablation study and discuss potential techniques that can further improve the performance, demonstrating great potential to deploy our method in real world food recognition applications.

show abstract

“…Liu et al [37] explored deep learning for food classification and achieved a competitive accuracy. Myers et al [38], Zhang et al [39], Subhi and Ali [40], Yanai and Kawano [41], Christodoulidis et al [42] Wu et al [43] focused on different variations of deep learning for classification of food data sets. Some of these studies generated their own food datasets while other studies used already available food benchmarks for evaluation of their proposed approaches.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

An Open-Ended Continual Learning for Food Recognition Using Class Incremental Extreme Learning Machines

Tahir

Loo

2020

IEEE Access

View full text Add to dashboard Cite

State-of-the-art deep learning models for food recognition do not allow data incremental learning and often suffer from catastrophic interference problems during the class incremental learning. This is an important issue in food recognition since real-world food datasets are open-ended and dynamic, involving a continuous increase in food samples and food classes. Model retraining is often carried out to cope with the dynamic nature of the data, but this demands high-end computational resources and significant time. This paper proposes a new open-ended continual learning framework by employing transfer learning on deep models for feature extraction, Relief F for feature selection, and a novel adaptive reduced class incremental kernel extreme learning machine (ARCIKELM) for classification. Transfer learning is beneficial due to the high generalization ability of deep learning features. Relief F reduces computational complexity by ranking and selecting the extracted features. The novel ARCIKELM classifier dynamically adjusts network architecture to reduce catastrophic forgetting. It addresses domain adaptation problems when new samples of the existing class arrive. To conduct comprehensive experiments, we evaluated the model against four standard food benchmarks and a recently collected Pakistani food dataset. Experimental results show that the proposed framework learns new classes incrementally with less catastrophic inference and adapts domain changes while having competitive classification performance. INDEX TERMS Food recognition, deep learning, open-ended continual learning, class incremental extreme learning machine, adaptive class incremental extreme learning machine, adaptive reduced class incremental kernel extreme learning machine.

show abstract

Learning to Make Better Mistakes

Cited by 55 publications

References 20 publications

Application of Deep Learning in Food: A Review

Application of Deep Learning in Food: A Review

Online Continual Learning For Visual Food Classification

An Open-Ended Continual Learning for Food Recognition Using Class Incremental Extreme Learning Machines

Contact Info

Product

Resources

About