MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection

Ma, Wenchi; Wu, Yuanwei; Wang, Zongbo; Wang, Guanghui

doi:10.1109/icpr.2018.8545693

Cited by 30 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning models: Inspired by the success of AlexNet [16] in the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2012, convolutional neural networks (CNN) have attracted a lot of attention and been successfully applied to image classification [20][21][22], object detection [4,23,24], depth estimation [25,26], image transformation [27,28], and crowd counting [29]citesajid2020plug. VGGNets [14], and GoogleNet [17], the ILSVRC winners of 2014 and 2015, proved that deeper models could significantly increase the ability of representations.…”

Section: Related Workmentioning

confidence: 99%

A comparative study on polyp classification using convolutional neural networks

Patel

Tao

et al. 2020

PLoS ONE

Self Cite

View full text Add to dashboard Cite

Colorectal cancer is the third most common cancer diagnosed in both men and women in the United States. Most colorectal cancers start as a growth on the inner lining of the colon or rectum, called 'polyp'. Not all polyps are cancerous, but some can develop into cancer. Early detection and recognition of the type of polyps is critical to prevent cancer and change outcomes. However, visual classification of polyps is challenging due to varying illumination conditions of endoscopy, variant texture, appearance, and overlapping morphology between polyps. More importantly, evaluation of polyp patterns by gastroenterologists is subjective leading to a poor agreement among observers. Deep convolutional neural networks have proven very successful in object classification across various object categories. In this work, we compare the performance of the state-of-the-art general object classification models for polyp classification. We trained a total of six CNN models end-to-end using a dataset of 157 video sequences composed of two types of polyps: hyperplastic and adenomatous. Our results demonstrate that the state-of-the-art CNN models can successfully classify polyps with an accuracy comparable or better than reported among gastroenterologists. The results of this study can guide future research in polyp classification.

show abstract

Section: Related Workmentioning

confidence: 99%

A comparative study on polyp classification using convolutional neural networks

Patel

Tao

et al. 2020

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thanks to the powerful capability of convolutional neural networks (CNN) in extracting image features, CNNbased deep learning models have achieved significant breakthroughs in various computer vision applications like classification [6], [22], segmentation [16], detection [30], tracking [49], image translation [46], and counting [39]. However, most of the current neural network models rely heavily on accurately labeled data.…”

Section: Introductionmentioning

confidence: 99%

Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

Yang¹,

Kim²,

Wang³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Adversarial training based on the maximum classifier discrepancy between the two classifier structures has achieved great success in unsupervised domain adaptation tasks for image classification. The approach adopts the structure of two classifiers, though simple and intuitive, the learned classification boundary may not well represent the data property in the new domain. In this paper, we propose to extend the structure to multiple classifiers to further boost its performance. To this end, we propose a very straightforward approach to adding more classifiers. We employ the principle that the classifiers are different from each other to construct a discrepancy loss function for multiple classifiers. Through the loss function construction method, we make it possible to add any number of classifiers to the original framework. The proposed approach is validated through extensive experimental evaluations. We demonstrate that, on average, adopting the structure of three classifiers normally yields the best performance as a tradeoff between the accuracy and efficiency. With minimum extra computational costs, the proposed approach can significantly improve the original algorithm.

show abstract

“…In recent years, deep convolutional neural networks (CNNs) have achieved huge success in many computer vision applications, such as image classification [6,28], object detection [27,37], tracking [62], segmentation [20,43], image generation [58], and crowd counting [48]. A lot of powerful network architectures have been proposed for efficient feature extraction, representation, and optimization [19,59,63].…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training

Yang,

Zhang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more domain invariant features. The proposed architecture can be applied to any model that utilizes domain invariant features for unsupervised domain adaptation to improve its ability to extract domain invariant features.We conduct experiments with the Domain-Adversarial Training of Neural Networks (DANN) model as a representative algorithm. In the training process, we supply the same input to the two modules and then extract their feature distribution and prediction results respectively. We propose a discrepancy loss to find the discrepancy of the prediction results and the feature distribution between the two modules. Through the adversarial training by maximizing the loss of their feature distribution and minimizing the discrepancy of their prediction results, the two modules are encouraged to learn more domain discriminative and domain invariant features respectively. Extensive comparative evaluations are conducted and the proposed approach outperforms the state-of-the-art in most unsupervised domain adaptation tasks.

show abstract

MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection

Cited by 30 publications

References 35 publications

A comparative study on polyp classification using convolutional neural networks

A comparative study on polyp classification using convolutional neural networks

Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training

Contact Info

Product

Resources

About