2022 14th International Conference on Machine Learning and Computing (ICMLC)最新文献_第2页

Few-Shot Learning in Object Classification using Meta-Learning with Between-Class Attribute Transfer 基于类间属性迁移的元学习在对象分类中的少射学习

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529914

Majed Alsadhan, W. Hsu

{"title":"Few-Shot Learning in Object Classification using Meta-Learning with Between-Class Attribute Transfer","authors":"Majed Alsadhan, W. Hsu","doi":"10.1145/3529836.3529914","DOIUrl":"https://doi.org/10.1145/3529836.3529914","url":null,"abstract":"We present a novel framework for the problem of transfer learning between few-shot source and target domains, using synthetic attributes in addition to convolutional neural networks that are pre-trained on larger image corpora. In these corpora, no labeled instances of the target domains are present, though they may contain instances of their superclasses. Using probabilistic inference over predicted classes and inferred attributes, we developed a meta-learning ensemble method that builds upon that of [10]. This paper introduces the new framework BCAT (Between-Class Attribute Transfer), adapting inter-class attribute transfer designed for zero-shot learning (ZSL), combined with fusing transfer learning and probabilistic priors, and thereby extending and improving upon existing deep meta-learning models for FSL. We show how probabilistic learning architectures can be adapted to use state-of-the-field deep learning components in this framework. We applied our technique to four baseline convnet-based FSL ensembles and boosted accuracy by up to 6.24% for 1-shot learning and up to 4.11% for 5-shot learning on the mini-ImageNet dataset, the best result of which is competitive with the current state of the field; using the same technique, we improved accuracy by up to 7.83% for 1-shot learning and up to 3.67% for 5-shot learning on the tiered-ImageNet dataset.","PeriodicalId":285191,"journal":{"name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127413790","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}

引用次数: 0

Deep-learning Based Denoising and Enhancement in Video Image of Approach Channel 基于深度学习的接近信道视频图像去噪与增强

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529919

Han Jiao, Peng Yuan, Jiaocheng Liu, Xujie Ren, Jufu Zhang

{"title":"Deep-learning Based Denoising and Enhancement in Video Image of Approach Channel","authors":"Han Jiao, Peng Yuan, Jiaocheng Liu, Xujie Ren, Jufu Zhang","doi":"10.1145/3529836.3529919","DOIUrl":"https://doi.org/10.1145/3529836.3529919","url":null,"abstract":"Due to the ubiquitous video sensor technology, it has become possible to build intelligent information system for the supervision of the approach channel. However, at present, there is still a technical problem to be solved, that is, the low-visibility video images taken in low-light environment have low brightness, low contrast and low signal-to-noise ratio. Meanwhile, they are also mixed with a lot of noise, which makes data extraction difficult. We propose a video image denoising and enhancement network based on deep learning, named DeNet, to improve the quality of low-light video images. DeNet consists of two parts: the first part is a deep residual network, which we named D-Net, to denoise the original video image. In the second part, we connect a D-Net network in parallel and add the normalization layer, which is used to fuse the features of the denoised image with the original image, and eventually realize the denoising and enhancement function. Experimental results on synthetic and real port test data sets show that our proposed method is superior to many advanced methods at present, and can meet the requirements of video denoising and enhancement of the approach channel.","PeriodicalId":285191,"journal":{"name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122222366","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}

引用次数: 0

Self-supervised Depth Estimation with High Resolution Features and Non-local Information 基于非局部信息和高分辨率特征的自监督深度估计

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529907

Rongying Jing, Yang Liu

{"title":"Self-supervised Depth Estimation with High Resolution Features and Non-local Information","authors":"Rongying Jing, Yang Liu","doi":"10.1145/3529836.3529907","DOIUrl":"https://doi.org/10.1145/3529836.3529907","url":null,"abstract":"Depth estimation is one of the most challenging tasks in computer vision, especially in self-supervised learning ways without restrictions of high-cost labels. Self-supervised depth estimation aims to infer three-dimensional space structures from two-dimensional planar images, only taking image pairs or sequences as supervision. Most existing methods adopt the encoder-decoder framework with skip-connection and recover the high-resolution depth maps from high-resolution low-level and low-resolution high-level feature maps. However, it is proved that high-resolution high-level feature maps, which are sensitive to illumination, color, texture, etc., are necessary for depth estimation. In this paper, we present a novel approach to extract high-level feature maps at all scales and introduce a self-attention mechanism to consider non-local features. The main improvements of our proposed method are two-fold:1) we combined the high-resolution feature extraction sub-network and extract high-resolution high-level features by connecting the high-to-low resolution convolution streams in parallel; 2) we embed the self-attention module with the features pyramid module(FPA) to obtain general context at large-scale features. The experiments evaluated on the KITTI benchmark have demonstrated that our network outperforms most existing methods and produces more accurate depth maps.","PeriodicalId":285191,"journal":{"name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131585405","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}

引用次数: 0

Classical Formula Nomenclature in Traditional Chinese Medicine based on Neural Network 基于神经网络的中药经典方剂命名

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529897

Chun Yin Lam, Saimei Li

{"title":"Classical Formula Nomenclature in Traditional Chinese Medicine based on Neural Network","authors":"Chun Yin Lam, Saimei Li","doi":"10.1145/3529836.3529897","DOIUrl":"https://doi.org/10.1145/3529836.3529897","url":null,"abstract":"Formula Nomenclature is an initial step to study Traditional Chinese Medicine (TCM) Prescription, especially for the Theory of Formula-Symptoms Correspondence in the Schools of Zhongjing (Shanghan), Koho and JingFang. It is common for a TCM practitioner to write only the Chinese medicinal composition in the prescription without any Formula name. Through generalising from the prescription the named prima-decoction, which helps to relieve the symptoms, the effectiveness of the decoction could then be evaluated. In this study, 261 Formulae and their compositions of 173 unique Chinese medicinals extracted from the original texts of the “Treatise on Cold Damage Disorders” and the “Synopsis of Prescriptions of the Golden Chamber” were used to train the classification model by neural network for Formula Nomenclature. The model was evaluated with satisfactory by a list of modified compositions from the selected decoctions representing different Meridians (see Table 2). The classification model trained could help in Formula Nomenclature by labelling the Formulae used in the prescription automatically and thereby the dimensionality of data could be minimised. This would also benefit in future the TCM research of Big Data, the assisted artificial intelligence prescription and expert system based on machine learning. To improve the model, further studies on identifying the sovereign, minister, assistant and courier roles of Chinese medicinals in Classical Formulae are recommended.","PeriodicalId":285191,"journal":{"name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134416924","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}

引用次数: 0

Based On Section Local Histogram Equalization Image Enhancement Algorithm 基于截面局部直方图均衡化的图像增强算法

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529946

Yanying Guo

引用次数: 0

3D-Based Facial Emotion Recognition using Depthwise Separable Convolution 基于深度可分离卷积的3d面部情感识别

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529855

H. S. Abubakar, M. M. Hossin, S. B. Yussif, Mandela Ali Margan Fargalla, Ramadhan Said Rashid, Yusuf Jamilu Umar, C. Ukwuoma, Ewald Erubaar Kuupole

引用次数: 1

Reparameterizing Residual Unit for Real-time Maritime Low-light image Enhancement 海上微光图像实时增强残差单元的再参数化

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529927

Zonglin Li

{"title":"Reparameterizing Residual Unit for Real-time Maritime Low-light image Enhancement","authors":"Zonglin Li","doi":"10.1145/3529836.3529927","DOIUrl":"https://doi.org/10.1145/3529836.3529927","url":null,"abstract":"Video surveillance is critical in the maritime industry. However, the inescapable low-light situation places a limitation on video surveillance advancement. At the same time, the high precision of deep learning brings high computational and memory requirements to its training and inference stages. However, high precision and high resource consumption are the characteristics of deep learning. To more effectively deploy the learning-based low-light enhancement method on the terminal device, we adopted the reparameterization technology in the enhancer model to reduce the number of additional calculations (named RepMConv). Specifically, we use linear combinations of inconsistent kernel sizes in the training phase and fold them back to normal convolutions in the inference phase. Convolution kernels with different sizes can effectively extract enhancer’s significant edge and texture information by providing different receptive fields. We first embed RepMConv into the residual block to improve the learning efficiency of the residual block. Finally, we complete our enhancer network in a multi-scale structure of encoder-decoder. Experimental results show that our proposed Enhancer can achieve high-quality maritime low-light image enhancement while maintaining breakneck inference speed.","PeriodicalId":285191,"journal":{"name":"2022 14th International Conference on Machine Learning and Computing (ICMLC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116745225","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}

引用次数: 0

Junction density based clustering algorithm for data with arbitrary shapes 基于结点密度的任意形状数据聚类算法

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529860

Ruijia Li, Zhiling Cai, Hong Wu

引用次数: 0

Learning-based Vulnerability Detection in Binary Code 基于学习的二进制代码漏洞检测

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529926

Amy Aumpansub, Zhen Huang

引用次数: 1

A Peer-to-Peer Distributed Bisecting K-means 点对点分布平分k均值

2022 14th International Conference on Machine Learning and Computing (ICMLC) Pub Date : 2022-02-18 DOI: 10.1145/3529836.3529895

Haoyuan Gao

引用次数: 0