Evolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization

Tan, Teck Yan; Zhang, Li; Lim, Chee Peng; Fielding, Ben; Yu, Yonghong; Anderson, Emma

doi:10.1109/access.2019.2903015

Cited by 99 publications

(54 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods such as these will be especially helpful on imbalanced data sets such as GTSRB. We also aim to explore hyper-parameter fine-tuning [51][52][53] using automated processes and parameter quantization techniques to further reduce the memory footprint of the proposed architecture.…”

Section: Discussionmentioning

confidence: 99%

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Lawrence

Zhang

2019

Sensors

Self Cite

View full text Add to dashboard Cite

Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43% with 39% fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49% with 31.8% fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5% with 0.38% fewer FLOPs.

show abstract

Section: Discussionmentioning

confidence: 99%

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Lawrence

Zhang

2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…These cropped images have similar intensity levels as those in ALL-IDB1, but different image dimensions. This dataset has been used for detection 25,26 , segmentation 27,28 and classification 29 .…”

Section: Dataset Descriptionmentioning

confidence: 99%

Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features

Sahlol

Kollmannsberger

Ewees

2020

Sci Rep

202

119

View full text Add to dashboard Cite

White Blood Cell (WBC) Leukaemia is caused by excessive production of leukocytes in the bone marrow, and image-based detection of malignant WBCs is important for its detection. Convolutional Neural Networks (CNNs) present the current state-of-the-art for this type of image classification, but their computational cost for training and deployment can be high. We here present an improved hybrid approach for efficient classification of WBC Leukemia. We first extract features from WBC images using VGGNet, a powerful CNN architecture, pre-trained on ImageNet. The extracted features are then filtered using a statistically enhanced Salp Swarm Algorithm (SESSA). This bio-inspired optimization algorithm selects the most relevant features and removes highly correlated and noisy features. We applied the proposed approach to two public WBC Leukemia reference datasets and achieve both high accuracy and reduced computational complexity. The SESSA optimization selected only 1 K out of 25 K features extracted with VGGNet, while improving accuracy at the same time. The results are among the best achieved on these datasets and outperform several convolutional network models. We expect that the combination of CNN feature extraction and SESSA feature optimization could be useful for many other image classification tasks.

show abstract

“…Furthermore, since convolutional neural networks (CNN) have been popularly used as the state of the art approaches in image recognition, we also compare our proposed ensemble learning approach with six pre-trained CNN models, namely, GoogLeNet, Inceptionv3, ResNet101, AlexNet, VGG16 and VGG19, while the pre-trained CNN models are used in the setting of transfer learning. In particular, following the popular way of experimental evaluation as adopted in related works on image recognition through deep learning (Fernandes et al, 2018;Fielding and Zhang, 2018;Sun et al, 2018;Tan et al, 2019), the experiments are conducted using holdout validation over 10 runs by randomly selecting 90% of the instances for training and the rest for testing in each run. These deep networks are pre-trained using a million images and are able to classify images into 1000 object categories.…”

Section: Experimental Studies Results and Discussionmentioning

confidence: 99%

Advancing Ensemble Learning Performance through data transformation and classifiers fusion in granular computing context

Liu

Zhang²

2019

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Classification is a special type of machine learning tasks, which is essentially achieved by training a classifier that can be used to classify new instances. In order to train a high performance classifier, it is crucial to extract representative features from raw data, such as text and images. In reality, instances could be highly diverse even if they belong to the same class, which indicates different instances of the same class could represent very different characteristics. For example, in a facial expression recognition task, some instances may be better described by Histogram of Oriented Gradients features, while others may be better presented by Local Binary Patterns features. From this point of view, it is necessary to adopt ensemble learning to train different classifiers on different feature sets and to fuse these classifiers towards more accurate classification of each instance. On the other hand, different algorithms are likely to show different suitability for training classifiers on different feature sets. It shows again the necessity to adopt ensemble learning towards advances in the classification performance. Furthermore, a multiclass classification task would become increasingly more complex when the number of classes is increased, i.e. it would lead to the increased difficulty in terms of discriminating different classes. In this paper, we propose an ensemble learning framework that involves transforming a multi-class classi

show abstract

Evolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization

Cited by 99 publications

References 42 publications

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features

Advancing Ensemble Learning Performance through data transformation and classifiers fusion in granular computing context

Contact Info

Product

Resources

About