Image Classification Using Convolutional Neural Networks and Kernel Extreme Learning Machines

Li, Zhuangzi; Zhu, Xiaobin; Wang, Lei; Guo, Ping

doi:10.1109/icip.2018.8451560

Cited by 18 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the ResNet50 [28] is the most widely used CNN architecture for food recognition problems, there are many results available for comparisons. So, the performance of the proposed two-scale CNN is compared with the previous methods [31]- [34] that are based on the ResNet50. ResNet-50 is a convolutional neural network with 50 layers and it has a fixed input size of 224 × 224.…”

Section: Methodsmentioning

confidence: 99%

Multi-Scale CNN for Fine-Grained Image Recognition

Won

2020

IEEE Access

View full text Add to dashboard Cite

Most conventional fine-grained image recognitions are based on a two-stream model of object-level and part-level CNNs, where the part-level CNN is responsible for learning the object-parts and their spatial relationships. To train the part-level CNN, we first need to separate parts from an object. However, there exist sub-level objects with no distinctive and separable parts. In this paper, a multi-scale CNN with a baseline Object-level and multiple Part-level CNNs is proposed for the fine-grained image recognition with no separable object-parts. The basic idea to train different CNNs of the multi-scale CNNs is to adopt different scales in resizing the training images. That is, the training images are resized such that the entire object appears as much as possible for the Object-level CNN, while only a local part of the object is to be included for the Part-level CNN. This scale-specific image resizing approach requires a scale-controllable parameter in the image resizing process. In this paper, a scale-controllable parameter is introduced for the linear-scaling and random-cropping method. Also, a line-based image resizing method with a scale-controllable parameter is employed for the part-level CNNs. The proposed multi-scale CNN is applied to a food image classification, which belongs to a fine-grained classification problem with no separable object-parts. Experimental results on the public food image datasets show that the classification accuracy improves substantially when the predicted scores of the multi-scale CNN are fused together. This reveals that the object-level and part-level CNNs work harmoniously in differentiating subtle differences of the sub-level objects.

show abstract

Section: Methodsmentioning

confidence: 99%

Multi-Scale CNN for Fine-Grained Image Recognition

Won

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…And it makes model to assign full probability to the ground truth label for each training sample, which potentially leads to overfit-ting. Therefore, they use other machine learning models (SVM [17], ELM [20], etc.) to replace it.…”

Section: Preclassificationmentioning

confidence: 99%

“…Each category has a minimum of 80 images. Following [20], we utilize 60 randomly selected images per class as the training dataset, the rest as the testing dataset. We resize all images to 256 × 256 pixels.…”

Section: Incomplete Label Rectified Labelmentioning

confidence: 99%

“…However, the softmax function encourages the output scores dramatically distinctive which potentially leads to overfitting. Some studies consider improving the discriminative ability of features by replacing softmax with other machine learning algorithms [17][18][19][20], e.g., Support Vector Machine (SVM) or Extreme Learning Machine (ELM). Although considerable progress has been achieved in image classification, existing traditional methods are still faced with some limitations: (1) extracting highdimensional features in matrix manipulation is timeconsuming and (2) most works rarely exploit the label-wise relation for image classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Label Rectification Learning through Kernel Extreme Learning Machine

Cai

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Along with the strong representation of the convolutional neural network (CNN), image classification tasks have achieved considerable progress. However, majority of works focus on designing complicated and redundant architectures for extracting informative features to improve classification performance. In this study, we concentrate on rectifying the incomplete outputs of CNN. To be concrete, we propose an innovative image classification method based on Label Rectification Learning (LRL) through kernel extreme learning machine (KELM). It mainly consists of two steps: (1) preclassification, extracting incomplete labels through a pretrained CNN, and (2) label rectification, rectifying the generated incomplete labels by the KELM to obtain the rectified labels. Experiments conducted on publicly available datasets demonstrate the effectiveness of our method. Notably, our method is extensible which can be easily integrated with off-the-shelf networks for improving performance.

show abstract

“…Stanford Dogs MIT Indoor 67 Method Acc (%) Method Acc (%) Method Acc (%) (Bossard, Guillaumin, and Van Gool 2014) 50.76 (Huang et al 2017) 78.30 (Milad and Subhasis 2016) 72.20 (Bossard, Guillaumin, and Van Gool 2014) 56.40 (Wei et al 2017) 78.86 (Dixit et al 2015) 72.86 (Meyers et al 2015) 79.00 (Chen and Zhang 2016) 79.50 (Lin, RoyChowdhury, and Maji 2018) 79.00 (Li et al 2018) 82.60 (Zhang et al 2016) 80.43 (Zhou et al 2018) 79.76 (Wei et al 2018) 85.70 (Dubey et al 2018) 83.75 (Yoo et al 2015) 80.78 (Guo et al 2018) 87.30 (Niu, Veeraraghavan, and Sabharwal 2018) 85.16 (Herranz, Jiang, and Li 2016) 80.97 (Hassannejad et al 2016) 88.28 (Krause et al 2016) 85.90 (Guo et al 2017) as D clean +f t), and previous works: Bottom-up , Pseudo-label (Lee 2013), Weakly (Joulin et al 2016), Boosting , PGM (Xiao et al 2015), WSL (Chen and Gupta 2015), Harnessing (Vo et al 2017), Goldfince (Krause et al 2016) that also employ and process web data for training CNN models. Different from the above methods which focus on data pre-processing, we optimize the model to learn from the web and standard data by reducing the influence of dataset gap.…”

Section: Food-101mentioning

confidence: 99%

Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

Sun

Chen

Yang

2019

AAAI

View full text Add to dashboard Cite

Fine-grained classification is absorbed in recognizing the subordinate categories of one field, which need a large number of labeled images, while it is expensive to label these images. Utilizing web data has been an attractive option to meet the demands of training data for convolutional neural networks (CNNs), especially when the well-labeled data is not enough. However, directly training on such easily obtained images often leads to unsatisfactory performance due to factors such as noisy labels. This has been conventionally addressed by reducing the noise level of web data. In this paper, we take a fundamentally different view and propose an adversarial discriminative loss to advocate representation coherence between standard and web data. This is further encapsulated in a simple, scalable and end-to-end trainable multi-task learning framework. We experiment on three public datasets using large-scale web data to evaluate the effectiveness and generalizability of the proposed approach. Extensive experiments demonstrate that our approach performs favorably against the state-of-the-art methods.

show abstract

Image Classification Using Convolutional Neural Networks and Kernel Extreme Learning Machines

Cited by 18 publications

References 14 publications

Multi-Scale CNN for Fine-Grained Image Recognition

Multi-Scale CNN for Fine-Grained Image Recognition

Label Rectification Learning through Kernel Extreme Learning Machine

Learning from Web Data Using Adversarial Discriminative Neural Networks for Fine-Grained Classification

Contact Info

Product

Resources

About