Pub Date : 2019-11-01DOI: 10.1109/ictai.2019.00001
{"title":"[Title page i]","authors":"","doi":"10.1109/ictai.2019.00001","DOIUrl":"https://doi.org/10.1109/ictai.2019.00001","url":null,"abstract":"","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131861228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00255
Lin Liu, D. Shi, Dansong Cheng, Maysam Orouskhani
In this paper, we propose a new and effective multi-objective optimization algorithm based on a modified harmony search. The proposed method employs reverse learning in the harmony vector updating equation in order to enhance the global searching ability. Moreover, it adopts a harmony anchoring scheme so that unnecessary exploration is avoided. Experimental studies carried on eight benchmark problems show quite satisfactory results and indicate the higher performance of the proposed algorithm in comparison with traditional multi-objective optimization algorithms. Finally, it has been applied to solve the image segmentation problem.
{"title":"An Advanced Harmony Search Algorithm Based on Harmony Anchoring and Reverse Learning","authors":"Lin Liu, D. Shi, Dansong Cheng, Maysam Orouskhani","doi":"10.1109/ICTAI.2019.00255","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00255","url":null,"abstract":"In this paper, we propose a new and effective multi-objective optimization algorithm based on a modified harmony search. The proposed method employs reverse learning in the harmony vector updating equation in order to enhance the global searching ability. Moreover, it adopts a harmony anchoring scheme so that unnecessary exploration is avoided. Experimental studies carried on eight benchmark problems show quite satisfactory results and indicate the higher performance of the proposed algorithm in comparison with traditional multi-objective optimization algorithms. Finally, it has been applied to solve the image segmentation problem.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132375785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00231
Matheus Gomes Sousa, K. Sakiyama, Lucas de Souza Rodrigues, Pedro Henrique de Moraes, Eraldo Rezende Fernandes, E. Matsubara
When breaking news occurs, stock quotes can change abruptly in a matter of seconds. The human analysis of breaking news can take several minutes, and investors in the financial markets need to make quick decisions. Such challenging scenarios require faster ways to support investors. In this work, we propose the use of bidirectional encoder representations from transformers BERT to perform sentiment analysis of news articles and provide relevant information for decision making in the stock market. This model is pre-trained on a large amount of general-domain documents by means of a self-learning task. To fine-tune this powerful model on sentiment analysis for the stock market, we manually labeled stock news articles as positive, neutral or negative. This dataset is freely available and amounts to 582 documents from several financial news sources. We fine-tune a BERT model on this dataset and achieve 72.5% of F-score. Then, we perform some experiments highlighting how the output of the obtained model can provide valuable information to predict the subsequent movements of the Dow Jones Industrial (DJI) Index.
{"title":"BERT for Stock Market Sentiment Analysis","authors":"Matheus Gomes Sousa, K. Sakiyama, Lucas de Souza Rodrigues, Pedro Henrique de Moraes, Eraldo Rezende Fernandes, E. Matsubara","doi":"10.1109/ICTAI.2019.00231","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00231","url":null,"abstract":"When breaking news occurs, stock quotes can change abruptly in a matter of seconds. The human analysis of breaking news can take several minutes, and investors in the financial markets need to make quick decisions. Such challenging scenarios require faster ways to support investors. In this work, we propose the use of bidirectional encoder representations from transformers BERT to perform sentiment analysis of news articles and provide relevant information for decision making in the stock market. This model is pre-trained on a large amount of general-domain documents by means of a self-learning task. To fine-tune this powerful model on sentiment analysis for the stock market, we manually labeled stock news articles as positive, neutral or negative. This dataset is freely available and amounts to 582 documents from several financial news sources. We fine-tune a BERT model on this dataset and achieve 72.5% of F-score. Then, we perform some experiments highlighting how the output of the obtained model can provide valuable information to predict the subsequent movements of the Dow Jones Industrial (DJI) Index.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"49 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132390038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
FPN (Feature Pyramid Networks) is one of the most popular object detection networks, which can improve small object detection by enhancing shallow features. However, limited attention has been paid to the improvement of large object detection via deeper feature enhancement. One existing approach merges the feature maps of different layers into a new feature map for object detection, but can lead to increased noise and loss of information. The other approach adds a bottom-up structure after the feature pyramid of FPN, which superimposes the information from shallow layers into the deep feature map but weakens the strength of FPN in detecting small objects. To address these challenges, this paper proposes TFPN (Twin Feature Pyramid Networks), which consists of (1) FPN+, a bottom-up structure that improves large object detection; (2) TPS, a Twin Pyramid Structure that improves medium object detection; and (3) innovative integration of these two with FPN, which can significantly improve the detection accuracy of large and medium objects while maintaining the advantage of FPN in small object detection. Extensive experiments using the MSCOCO object detection datasets and the BDD100K automatic driving dataset demonstrate that TFPN significantly improves over existing models, achieving up to 2.2 improvement in detection accuracy (e.g., 36.3 for FPN vs. 38.5 for TFPN on COCO Val-17). Our method can obtain the same accuracy as FPN with ResNet-101 based on ResNet-50 and needs fewer parameters.
特征金字塔网络(Feature Pyramid Networks，简称FPN)是目前最流行的目标检测网络之一，它可以通过增强浅层特征来改善小目标的检测。然而，通过更深层次的特征增强来改进大目标检测的研究却很少。现有的一种方法是将不同层的特征图合并成一个新的特征图用于目标检测，但这可能导致噪声增加和信息丢失。另一种方法是在FPN的特征金字塔之后增加一个自下而上的结构，将浅层信息叠加到深层特征图中，但削弱了FPN检测小目标的强度。为了解决这些挑战，本文提出了TFPN(双特征金字塔网络)，它包括:(1)FPN+，一种自下而上的结构，可以提高大型目标的检测;(2) TPS，双金字塔结构，提高介质目标检测;(3)二者与FPN的创新融合，在保持FPN在小目标检测中的优势的同时，显著提高了大中型目标的检测精度。使用MSCOCO目标检测数据集和BDD100K自动驾驶数据集进行的大量实验表明，TFPN比现有模型有了显著改善，检测精度提高了2.2(例如，FPN的36.3比COCO var -17上的TFPN的38.5)。该方法可以获得与基于ResNet-50的ResNet-101的FPN相同的精度，并且需要更少的参数。
{"title":"TFPN: Twin Feature Pyramid Networks for Object Detection","authors":"Yi Liang, Changjian Wang, Fangzhao Li, Yuxing Peng, Q. Lv, Yuan Yuan, Zhen Huang","doi":"10.1109/ICTAI.2019.00251","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00251","url":null,"abstract":"FPN (Feature Pyramid Networks) is one of the most popular object detection networks, which can improve small object detection by enhancing shallow features. However, limited attention has been paid to the improvement of large object detection via deeper feature enhancement. One existing approach merges the feature maps of different layers into a new feature map for object detection, but can lead to increased noise and loss of information. The other approach adds a bottom-up structure after the feature pyramid of FPN, which superimposes the information from shallow layers into the deep feature map but weakens the strength of FPN in detecting small objects. To address these challenges, this paper proposes TFPN (Twin Feature Pyramid Networks), which consists of (1) FPN+, a bottom-up structure that improves large object detection; (2) TPS, a Twin Pyramid Structure that improves medium object detection; and (3) innovative integration of these two with FPN, which can significantly improve the detection accuracy of large and medium objects while maintaining the advantage of FPN in small object detection. Extensive experiments using the MSCOCO object detection datasets and the BDD100K automatic driving dataset demonstrate that TFPN significantly improves over existing models, achieving up to 2.2 improvement in detection accuracy (e.g., 36.3 for FPN vs. 38.5 for TFPN on COCO Val-17). Our method can obtain the same accuracy as FPN with ResNet-101 based on ResNet-50 and needs fewer parameters.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132402450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00182
Junsha Chen, Neng Gao, Cong Xue, Yifei Zhang, Chenyang Tu, Min Li
Detecting local topic from social media is an important task for many applications, such as local event discovery and activity recommendation. Recent years have witnessed growing interest in utilizing spatio-temporal social media for local topic detection. However, conventional topic models consider keywords as independent items, which suffer great limitations in modeling short texts from social media. Therefore, some studies introduce embedding into topic models to preserve the semantic correlation among keywords of short texts. Nevertheless, due to the lack of rich contexts in social media, the performance of these embedding based topic models still remain unsatisfactory. In order to enrich the contexts of keywords, we propose two network based embedding methods, both of which can generate rich contexts for keywords by random walks and produce coherent keyword embeddings for topic modeling. Besides, processing continuous spatio-temporal information in social media is also very challenging. Most of the existing methods simply split time and location into equal-size units, which fall short in capturing the continuity of spatio-temporal information. To address this issue, we present a hotspot detection algorithm to identify spatial and temporal hotspots, which can address spatio-temporal continuity and alleviate data sparsity. Finally, the experiments show that the performance of our methods has been improved significantly compared to the state-of-the-art methods.
{"title":"The Application of Network Based Embedding in Local Topic Detection from Social Media","authors":"Junsha Chen, Neng Gao, Cong Xue, Yifei Zhang, Chenyang Tu, Min Li","doi":"10.1109/ICTAI.2019.00182","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00182","url":null,"abstract":"Detecting local topic from social media is an important task for many applications, such as local event discovery and activity recommendation. Recent years have witnessed growing interest in utilizing spatio-temporal social media for local topic detection. However, conventional topic models consider keywords as independent items, which suffer great limitations in modeling short texts from social media. Therefore, some studies introduce embedding into topic models to preserve the semantic correlation among keywords of short texts. Nevertheless, due to the lack of rich contexts in social media, the performance of these embedding based topic models still remain unsatisfactory. In order to enrich the contexts of keywords, we propose two network based embedding methods, both of which can generate rich contexts for keywords by random walks and produce coherent keyword embeddings for topic modeling. Besides, processing continuous spatio-temporal information in social media is also very challenging. Most of the existing methods simply split time and location into equal-size units, which fall short in capturing the continuity of spatio-temporal information. To address this issue, we present a hotspot detection algorithm to identify spatial and temporal hotspots, which can address spatio-temporal continuity and alleviate data sparsity. Finally, the experiments show that the performance of our methods has been improved significantly compared to the state-of-the-art methods.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131539046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00192
Ashish Rana, A. Malhi, Kary Främling
Neural networks are not great generalizers outside their training range i.e. they are good at capturing bias but might miss the overall concept. Important issues with neural networks is that when testing data goes outside training range they fail to predict accurate results. Hence, they loose the ability to generalize a concept. For systematic numeric exploration neural accumulators (NAC) and neural arithmetic logic unit(NALU) are proposed which performs excellent for simple arithmetic operations. But, major limitation with these units is that they can't handle complex mathematical operations & equations. For example, NALU can predict accurate results for multiplication operation but not for factorial function which is essentially composition of multiplication operations only. It is unable to comprehend pattern behind an expression when composition of operations are involved. Hence, we propose a new neural network structure effectively which takes in complex compositional mathematical operations and produces best possible results with small NALU based neural networks as its pluggable modules which evaluates these expression at unitary level in a bottom-up manner. We call this effective neural network as CalcNet, as it helps in predicting accurate calculations for complex numerical expressions even for values that are out of training range. As part of our study we applied this network on numerically approximating complex equations, evaluating biquadratic equations and tested reusability of these modules. We arrived at far better generalizations for complex arithmetic extrapolation tasks as compare to both only NALU layer based neural networks and simple feed forward neural networks. Also, we achieved even better results for our golden ratio based modified NAC and NALU structures for both interpolating and extrapolating tasks in all evaluation experiments. Finally, from reusability standpoint this model demonstrate strong invariance for making predictions on different tasks.
{"title":"Exploring Numerical Calculations with CalcNet","authors":"Ashish Rana, A. Malhi, Kary Främling","doi":"10.1109/ICTAI.2019.00192","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00192","url":null,"abstract":"Neural networks are not great generalizers outside their training range i.e. they are good at capturing bias but might miss the overall concept. Important issues with neural networks is that when testing data goes outside training range they fail to predict accurate results. Hence, they loose the ability to generalize a concept. For systematic numeric exploration neural accumulators (NAC) and neural arithmetic logic unit(NALU) are proposed which performs excellent for simple arithmetic operations. But, major limitation with these units is that they can't handle complex mathematical operations & equations. For example, NALU can predict accurate results for multiplication operation but not for factorial function which is essentially composition of multiplication operations only. It is unable to comprehend pattern behind an expression when composition of operations are involved. Hence, we propose a new neural network structure effectively which takes in complex compositional mathematical operations and produces best possible results with small NALU based neural networks as its pluggable modules which evaluates these expression at unitary level in a bottom-up manner. We call this effective neural network as CalcNet, as it helps in predicting accurate calculations for complex numerical expressions even for values that are out of training range. As part of our study we applied this network on numerically approximating complex equations, evaluating biquadratic equations and tested reusability of these modules. We arrived at far better generalizations for complex arithmetic extrapolation tasks as compare to both only NALU layer based neural networks and simple feed forward neural networks. Also, we achieved even better results for our golden ratio based modified NAC and NALU structures for both interpolating and extrapolating tasks in all evaluation experiments. Finally, from reusability standpoint this model demonstrate strong invariance for making predictions on different tasks.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117279029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00035
Len Du
In this paper we show how to implement a deep neural network that is strictly equivalent (sans floating-point errors) to the verbatim (batch) k-means algorithm or Lloyd's algorithm, when trained with gradient descent. Most interestingly, doing so shows that the k-means algorithm, a staple of "conventional'" or "shallow'" machine learning, can actually be seen as a special case of deep learning, contrary to the general perception that deep learning is a subset of machine learning. Doing so also automatically introduces yet another unsupervised learning technique into the arsenal of deep learning, which happens to be an example of interpretable deep neural networks as well. Finally, we also show how to utilize the powerful deep learning infrastructures with very little extra effort for adaptation.
{"title":"Shallow Deep Learning: Embedding Verbatim K-Means in Deep Neural Networks","authors":"Len Du","doi":"10.1109/ICTAI.2019.00035","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00035","url":null,"abstract":"In this paper we show how to implement a deep neural network that is strictly equivalent (sans floating-point errors) to the verbatim (batch) k-means algorithm or Lloyd's algorithm, when trained with gradient descent. Most interestingly, doing so shows that the k-means algorithm, a staple of \"conventional'\" or \"shallow'\" machine learning, can actually be seen as a special case of deep learning, contrary to the general perception that deep learning is a subset of machine learning. Doing so also automatically introduces yet another unsupervised learning technique into the arsenal of deep learning, which happens to be an example of interpretable deep neural networks as well. Finally, we also show how to utilize the powerful deep learning infrastructures with very little extra effort for adaptation.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114931452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00053
Xu Zhang, Xin Tian, Bing Yang, Zuyu Zhang, Yan Li
Unlabeled data can be easily collected and help to exploit the correlations among different modalities. Existing works tried to explore label information contained in unlabeled data, however most of them suffer from difficulties in separating samples from different categories and have great interference. This paper proposes a novel method named semi-supervised cross-modal hashing based on label prediction and distance preserving(SS-LPDP). First, we use the deep neural networks to extract the feature of the labeled data among different modalities and get the feature distribution of each category. Second, the similarity of the data among different modalities is maximized based on the extracted feature and the label information. A common objective function is proposed with distance preserving constraint, which can effectively separate data into different categories and reduce interference in retrieval. An optimization algorithm is used to update the network parameters of feature learning in each modality, and the label information of unlabeled data are dynamically updated according to the changes of the feature distribution in each iteration. Experimental evaluation on Wiki, Pascal and NUS-WIDE datasets show that the proposed method outperforms recent methods when we set 25% samples without category labels.
{"title":"Semi-Supervised Cross-Modal Hashing Based on Label Prediction and Distance Preserving","authors":"Xu Zhang, Xin Tian, Bing Yang, Zuyu Zhang, Yan Li","doi":"10.1109/ICTAI.2019.00053","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00053","url":null,"abstract":"Unlabeled data can be easily collected and help to exploit the correlations among different modalities. Existing works tried to explore label information contained in unlabeled data, however most of them suffer from difficulties in separating samples from different categories and have great interference. This paper proposes a novel method named semi-supervised cross-modal hashing based on label prediction and distance preserving(SS-LPDP). First, we use the deep neural networks to extract the feature of the labeled data among different modalities and get the feature distribution of each category. Second, the similarity of the data among different modalities is maximized based on the extracted feature and the label information. A common objective function is proposed with distance preserving constraint, which can effectively separate data into different categories and reduce interference in retrieval. An optimization algorithm is used to update the network parameters of feature learning in each modality, and the label information of unlabeled data are dynamically updated according to the changes of the feature distribution in each iteration. Experimental evaluation on Wiki, Pascal and NUS-WIDE datasets show that the proposed method outperforms recent methods when we set 25% samples without category labels.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114945307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00130
Yusuke Ohtsubo, Tetsu Matsukawa, Einoshin Suzuki
We propose a GAN-based one-shot generation method on a fine-grained category, which represents a subclass of a category, typically with diverse examples. One-shot generation refers to a task of taking an image which belongs to a class not used in the training phase and then generating a set of new images belonging to the same class. Generative Adversarial Network (GAN), which represents a type of deep neural networks with competing generator and discriminator, has proven to be useful in generating realistic images. Especially DAGAN, which maps the input image to a low-dimensional space via an encoder and then back to the example space via a decoder, has been quite effective with datasets such as handwritten character datasets. However, when the class corresponds to a fine-grained category, DAGAN occasionally generates images which are regarded as belonging to other classes due to the rich variety of the examples in the class and the low dissimilarities of the examples among the classes. For example, it accidentally generates facial images of different persons when the class corresponds to a specific person. To circumvent this problem, we introduce a metric learning with a triplet loss to the bottleneck layer of DAGAN to penalize such a generation. We also extend the optimization algorithm of DAGAN to an alternating procedure for two types of loss functions. Our proposed method outperforms DAGAN in the GAN-test task for VGG-Face dataset and CompCars dataset by 5.6% and 4.8% in accuracy, respectively. We also conducted experiments for the data augmentation task and observed 4.5% higher accuracy for our proposed method over DAGAN for VGG-Face dataset.
{"title":"Harnessing GAN with Metric Learning for One-Shot Generation on a Fine-Grained Category","authors":"Yusuke Ohtsubo, Tetsu Matsukawa, Einoshin Suzuki","doi":"10.1109/ICTAI.2019.00130","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00130","url":null,"abstract":"We propose a GAN-based one-shot generation method on a fine-grained category, which represents a subclass of a category, typically with diverse examples. One-shot generation refers to a task of taking an image which belongs to a class not used in the training phase and then generating a set of new images belonging to the same class. Generative Adversarial Network (GAN), which represents a type of deep neural networks with competing generator and discriminator, has proven to be useful in generating realistic images. Especially DAGAN, which maps the input image to a low-dimensional space via an encoder and then back to the example space via a decoder, has been quite effective with datasets such as handwritten character datasets. However, when the class corresponds to a fine-grained category, DAGAN occasionally generates images which are regarded as belonging to other classes due to the rich variety of the examples in the class and the low dissimilarities of the examples among the classes. For example, it accidentally generates facial images of different persons when the class corresponds to a specific person. To circumvent this problem, we introduce a metric learning with a triplet loss to the bottleneck layer of DAGAN to penalize such a generation. We also extend the optimization algorithm of DAGAN to an alternating procedure for two types of loss functions. Our proposed method outperforms DAGAN in the GAN-test task for VGG-Face dataset and CompCars dataset by 5.6% and 4.8% in accuracy, respectively. We also conducted experiments for the data augmentation task and observed 4.5% higher accuracy for our proposed method over DAGAN for VGG-Face dataset.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115619919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-01DOI: 10.1109/ICTAI.2019.00113
Xinyu Zhou, Yiwen Ling, M. Zhong, Mingwen Wang
As a relatively new paradigm of bio-inspired optimization techniques, artificial bee colony (ABC) algorithm has attracted much attention for its simplicity and effectiveness. However, the performance of ABC is not satisfactory when solving some complex optimization problems. To improve its performance, we propose a novel ABC variant by designing a dynamic multi-population scheme (DMPS). In DMPS, the population is divided into several subpopulations, and the size of subpopulation is adjusted dynamically by checking the quality of the global best solution. Moreover, we design two novel solution search equations to maximize the effectiveness of DMPS, in which the local best solution of each subpopulation and the global best solution of the whole population are utilized simultaneously. In the experiments, 32 widely used benchmark functions are used, and four well-established ABC variants are involved in the comparison. The comparative results show that our approach performs better on the majority of benchmark functions.
{"title":"Dynamic Multi-population Artificial Bee Colony Algorithm","authors":"Xinyu Zhou, Yiwen Ling, M. Zhong, Mingwen Wang","doi":"10.1109/ICTAI.2019.00113","DOIUrl":"https://doi.org/10.1109/ICTAI.2019.00113","url":null,"abstract":"As a relatively new paradigm of bio-inspired optimization techniques, artificial bee colony (ABC) algorithm has attracted much attention for its simplicity and effectiveness. However, the performance of ABC is not satisfactory when solving some complex optimization problems. To improve its performance, we propose a novel ABC variant by designing a dynamic multi-population scheme (DMPS). In DMPS, the population is divided into several subpopulations, and the size of subpopulation is adjusted dynamically by checking the quality of the global best solution. Moreover, we design two novel solution search equations to maximize the effectiveness of DMPS, in which the local best solution of each subpopulation and the global best solution of the whole population are utilized simultaneously. In the experiments, 32 widely used benchmark functions are used, and four well-established ABC variants are involved in the comparison. The comparative results show that our approach performs better on the majority of benchmark functions.","PeriodicalId":346657,"journal":{"name":"2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116179845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：