|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | YOLOP:You Only Look Once for Panoptic Driving Perception显示文摘A panoptic driving perception system is an essential part of autonomous driving.A high-precision and real-time perception system can assist the vehicle in making reasonable decisions while driving.We present a panoptic driving perception network(you only look once for panoptic(YOLOP))to perform traffic object detection,drivable area segmentation,and lane detection simultaneously.It is composed of one encoder for feature extraction and three decoders to handle the specific tasks.Our model performs extremely well on the challenging BDD100K dataset,achieving state-of-the-art on all three tasks in terms of accuracy and speed.Besides,we verify the effectiveness of our multi-task learning model for joint training via ablative studies.To our best knowledge,this is the first work that can process these three visual perception tasks simultaneously in real-time on an embedded device Jetson TX2(23 FPS),and maintain excellent accuracy.To facilitate further research,the source codes and pre-trained models are released at http://gffzz188fe103f8f1460as9wnwfvoqq9wp6nvx.ffgz.tsg.suse.edu.cn/hustvl/YOLOP. | Dong Wu Man-Wen Liao Wei-Tian Zhang Xing-Gang Wang Xiang Bai Wen-Qing Cheng Wen-Yu Liu | 2022 | Machine Intelligence Research2022，19，6： | 8 |
| 2 | Multi-dimensional Classification via Selective Feature Augmentation显示文摘In multi-dimensional classification(MDC), the semantics of objects are characterized by multiple class spaces from different dimensions. Most MDC approaches try to explicitly model the dependencies among class spaces in output space. In contrast, the recently proposed feature augmentation strategy, which aims at manipulating feature space, has also been shown to be an effective solution for MDC. However, existing feature augmentation approaches only focus on designing holistic augmented features to be appended with the original features, while better generalization performance could be achieved by exploiting multiple kinds of augmented features.In this paper, we propose the selective feature augmentation strategy that focuses on synergizing multiple kinds of augmented features.Specifically, by assuming that only part of the augmented features is pertinent and useful for each dimension′s model induction, we derive a classification model which can fully utilize the original features while conduct feature selection for the augmented features. To validate the effectiveness of the proposed strategy, we generate three kinds of simple augmented features based on standard k NN, weighted k NN, and maximum margin techniques, respectively. Comparative studies show that the proposed strategy achieves superior performance against both state-of-the-art MDC approaches and its degenerated versions with either kind of augmented features. | Bin-Bin Jia Min-Ling Zhang | 2022 | Machine Intelligence Research2022，19，1： | 5 |
| 3 | Paradigm Shift in Natural Language Processing显示文摘In the era of deep learning, modeling for most natural language processing (NLP) tasks has converged into several mainstream paradigms. For example, we usually adopt the sequence labeling paradigm to solve a bundle of tasks such as POS-tagging, named entity recognition (NER), and chunking, and adopt the classification paradigm to solve tasks like sentiment analysis. With the rapid progress of pre-trained language models, recent years have witnessed a rising trend of paradigm shift, which is solving one NLP task in a new paradigm by reformulating the task. The paradigm shift has achieved great success on many tasks and is becoming a promising way to improve model performance. Moreover, some of these paradigms have shown great potential to unify a large number of NLP tasks, making it possible to build a single model to handle diverse tasks. In this paper, we review such phenomenon of paradigm shifts in recent years, highlighting several paradigms that have the potential to solve different NLP tasks. | Tian-Xiang Sun Xiang-Yang Liu Xi-Peng Qiu Xuan-Jing Huang | 2022 | Machine Intelligence Research2022，19，3： | 4 |
| 4 | Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey显示文摘With the urgent demand for generalized deep models,many pre-trained big models are proposed,such as bidirectional encoder representations(BERT),vision transformer(ViT),generative pre-trained transformers(GPT),etc.Inspired by the success of these models in single domains(like computer vision and natural language processing),the multi-modal pre-trained big models have also drawn more and more attention in recent years.In this work,we give a comprehensive survey of these models and hope this paper could provide new insights and helps fresh researchers to track the most cutting-edge works.Specifically,we firstly introduce the background of multi-modal pre-training by reviewing the conventional deep learning,pre-training works in natural language process,computer vision,and speech.Then,we introduce the task definition,key challenges,and advantages of multi-modal pre-training models(MM-PTMs),and discuss the MM-PTMs with a focus on data,objectives,network architectures,and knowledge enhanced pre-training.After that,we introduce the downstream tasks used for the validation of large-scale MM-PTMs,including generative,classification,and regression tasks.We also give visualization and analysis of the model parameters and results on representative downstream tasks.Finally,we point out possible research directions for this topic that may benefit future works.In addition,we maintain a continuously updated paper list for large-scale pre-trained multi-modal big models:http://gffzz188fe103f8f1460as9wnwfvoqq9wp6nvx.ffgz.tsg.suse.edu.cn/wangxiao5791509/MultiModal_BigModels_Survey. | Xiao Wang Guangyao Chen Guangwu Qian Pengcheng Gao Xiao-Yong Wei Yaowei Wang Yonghong Tian Wen Gao | 2023 | Machine Intelligence Research2023，20，4： | 3 |
| 5 | A Review of Predictive and Contrastive Self-supervised Learning for Medical Images显示文摘Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks. But, the application of deep learning in medical image analysis is limited by the scarcity of high-quality annotated medical imaging data. An emerging solution is self-supervised learning (SSL), among which contrastive SSL is the most successful approach to rivalling or outperforming supervised learning. This review investigates several state-of-the-art contrastive SSL algorithms originally on natural images as well as their adaptations for medical images, and concludes by discussing recent advances, current limitations, and future directions in applying contrastive SSL in the medical domain. | Wei-Chien Wang Euijoon Ahn Dagan Feng Jinman Kim | 2023 | Machine Intelligence Research2023，20，4： | 2 |
| 6 | Correction to:YOLOP:You Only Look Once for Panoptic Driving Perception显示文摘Correction to:YOLOP:You Only Look Once for Panoptic Driving Perception DOI:10.1007/s11633-022-1339-y Authors:Dong Wu,Man-Wen Liao,Wei-Tian Zhang,Xing-Gang Wang,Xiang Bai,Wen-Qing Cheng,Wen-Yu Liu The article YOLOP:You Only Look Once for Panoptic Driving Perception,written by Dong Wu,Man-Wen Liao,Wei-Tian Zhang,Xing-Gang Wang,Xiang Bai,Wen-Qing Cheng,Wen-Yu Liu,was originally published without Open Access. | Dong Wu Man-Wen Liao Wei-Tian Zhang Xing-Gang Wang Xiang Bai Wen-Qing Cheng Wen-Yu Liu | 2023 | Machine Intelligence Research2023，20，6： | 2 |
| 7 | VLP:A Survey on Vision-language Pre-training显示文摘In the past few years,the emergence of pre-training models has brought uni-modal fields such as computer vision(CV)and natural language processing(NLP)to a new era.Substantial works have shown that they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch.So can such pre-trained models be applied to multi-modal tasks?Researchers have ex-plored this problem and made significant progress.This paper surveys recent advances and new frontiers in vision-language pre-training(VLP),including image-text and video-text pre-training.To give readers a better overall grasp of VLP,we first review its recent ad-vances in five aspects:feature extraction,model architecture,pre-training objectives,pre-training datasets,and downstream tasks.Then,we summarize the specific VLP models in detail.Finally,we discuss the new frontiers in VLP.To the best of our knowledge,this is the first survey focused on VLP.We hope that this survey can shed light on future research in the VLP field. | Fei-Long Chen Du-Zhen Zhang Ming-Lun Han Xiu-Yi Chen Jing Shi Shuang Xu Bo Xu | 2023 | Machine Intelligence Research2023，20，1： | 2 |
| 8 | Video Polyp Segmentation: A Deep Learning Perspective显示文摘We present the first comprehensive video polyp segmentation(VPS)study in the deep learning era.Over the years,developments in VPS are not moving forward with ease due to the lack of a large-scale dataset with fine-grained segmentation annotations.To address this issue,we first introduce a high-quality frame-by-frame annotated VPS dataset,named SUN-SEG,which contains 158690colonoscopy video frames from the well-known SUN-database.We provide additional annotation covering diverse types,i.e.,attribute,object mask,boundary,scribble,and polygon.Second,we design a simple but efficient baseline,named PNS+,which consists of a global encoder,a local encoder,and normalized self-attention(NS)blocks.The global and local encoders receive an anchor frame and multiple successive frames to extract long-term and short-term spatial-temporal representations,which are then progressively refined by two NS blocks.Extensive experiments show that PNS+achieves the best performance and real-time inference speed(170 fps),making it a promising solution for the VPS task.Third,we extensively evaluate 13 representative polyp/object segmentation models on our SUN-SEG dataset and provide attribute-based comparisons.Finally,we discuss several open issues and suggest possible research directions for the VPS community.Our project and dataset are publicly available at http://gffzz188fe103f8f1460as9wnwfvoqq9wp6nvx.ffgz.tsg.suse.edu.cn/GewelsJI/VPS. | Ge-Peng Ji Guobao Xiao Yu-Cheng Chou Deng-Ping Fan Kai Zhao Geng Chen Luc Van Gool | 2022 | Machine Intelligence Research2022，19，6： | 2 |
| 9 | Evolutionary Computation for Expensive Optimization:A Survey显示文摘Expensive optimization problem(EOP) widely exists in various significant real-world applications. However, EOP requires expensive or even unaffordable costs for evaluating candidate solutions, which is expensive for the algorithm to find a satisfactory solution. Moreover, due to the fast-growing application demands in the economy and society, such as the emergence of the smart cities, the internet of things, and the big data era, solving EOP more efficiently has become increasingly essential in various fields, which poses great challenges on the problem-solving ability of optimization approach for EOP. Among various optimization approaches, evolutionary computation(EC) is a promising global optimization tool widely used for solving EOP efficiently in the past decades. Given the fruitful advancements of EC for EOP, it is essential to review these advancements in order to synthesize and give previous research experiences and references to aid the development of relevant research fields and real-world applications. Motivated by this, this paper aims to provide a comprehensive survey to show why and how EC can solve EOP efficiently. For this aim, this paper firstly analyzes the total optimization cost of EC in solving EOP. Then, based on the analysis, three promising research directions are pointed out for solving EOP, which are problem approximation and substitution, algorithm design and enhancement, and parallel and distributed computation. Note that, to the best of our knowledge, this paper is the first that outlines the possible directions for efficiently solving EOP by analyzing the total expensive cost. Based on this, existing works are reviewed comprehensively via a taxonomy with four parts, including the above three research directions and the real-world application part. Moreover, some future research directions are also discussed in this paper. It is believed that such a survey can attract attention, encourage discussions, and stimulate new EC research ideas for solving EOP and related real-world applications more efficiently. | Jian-Yu Li Zhi-Hui Zhan Jun Zhang | 2022 | Machine Intelligence Research2022，19，1： | 2 |
| 10 | Probability Enhanced Entropy(PEE) Novel Feature for Improved Bird Sound Classification显示文摘Identification of bird species from their sounds has become an important area in biodiversity-related research due to the relative ease of capturing bird sounds in the commonly challenging habitat. Audio features have a massive impact on the classification task since they are the fundamental elements used to differentiate classes. As such, the extraction of informative properties of the data is a crucial stage of any classification-based application. Therefore, it is vital to identify the most significant feature to represent the actual bird sounds. In this paper, we propose a novel feature that can advance classification accuracy with modified features, which are most suitable for classifying birds from its audio sounds. Modified Gammatone frequency cepstral coefficient(GTCC) features have been extracted with their frequency banks adjusted to suit bird sounds. The features are then used to train and test a support vector machine(SVM) classifier. It has been shown that the modified GTCC features are able to give 86% accuracy with twenty Bornean birds. Furthermore, in this paper, we are proposing a novel probability enhanced entropy(PEE) feature, which, when combined with the modified GTCC features, is able to improve accuracy further to 89.5%. These results are significant as the relatively low-resource intensive SVM with the proposed modified GTCC, and the proposed novel PEE feature can be implemented in a real-time system to assist researchers,scientists, conservationists, and even eco-tourists in identifying bird species in the dense forest. | Ramashini Murugaiya Pg Emeroylariffion Abas Liyanage Chandratilak De Silva | 2022 | Machine Intelligence Research2022，19，1： | 2 |
| 11 | Towards a New Paradigm for Brain-inspired Computer Vision显示文摘Brain-inspired computer vision aims to learn from biological systems to develop advanced image processing techniques.However,its progress so far is not impressing.We recognize that a main obstacle comes from that the current paradigm for brain-inspired computer vision has not captured the fundamental nature of biological vision,i.e.,the biological vision is targeted for processing spatio-temporal patterns.Recently,a new paradigm for developing brain-inspired computer vision is emerging,which emphasizes on the spatio-temporal nature of visual signals and the brain-inspired models for processing this type of data.In this paper,we review some recent primary works towards this new paradigm,including the development of spike cameras which acquire spiking signals directly from visual scenes,and the development of computational models learned from neural systems that are specialized to process spatio-temporal patterns,including models for object detection,tracking,and recognition.We also discuss about the future directions to improve the paradigm. | Xiao-Long Zou Tie-Jun Huang Si Wu | 2022 | Machine Intelligence Research2022，19，5： | 1 |
| 12 | Causal Reasoning Meets Visual Representation Learning: A Prospective Study显示文摘Visual representation learning is ubiquitous in various real-world applications,including visual comprehension,video understanding,multi-modal analysis,human-computer interaction,and urban computing.Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era,the lack of interpretability,robustness,and out-of-distribution generalization are becoming the challenges of the existing visual models.The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge,which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities.Inspired by the strong inference ability of human-level agents,recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability.In this paper,we conduct a comprehensive review of existing causal reasoning methods for visual representation learning,covering fundamental theories,models,and datasets.The limitations of current methods and datasets are also discussed.Moreover,we propose some prospective challenges,opportunities,and future research directions for benchmarking causal reasoning algorithms in visual representation learning.This paper aims to provide a comprehensive overview of this emerging field,attract attention,encourage discussions,bring to the forefront the urgency of developing novel causal reasoning methods,publicly available benchmarks,and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently. | Yang Liu Yu-Shen Wei Hong Yan Guan-Bin Li Liang Lin | 2022 | Machine Intelligence Research2022，19，6： | 1 |
| 13 | Glaucoma Detection with Retinal Fundus Images Using Segmentation and Classification显示文摘Glaucoma is a prevalent cause of blindness worldwide.If not treated promptly,it can cause vision and quality of life to deteriorate.According to statistics,glaucoma affects approximately 65 million individuals globally.Fundus image segmentation depends on the optic disc(OD)and optic cup(OC).This paper proposes a computational model to segment and classify retinal fundus images for glaucoma detection.Different data augmentation techniques were applied to prevent overfitting while employing several data pre-processing approaches to improve the image quality and achieve high accuracy.The segmentation models are based on an attention U-Net with three separate convolutional neural networks(CNNs)backbones:Inception-v3,visual geometry group 19(VGG19),and residual neural network 50(ResNet50).The classification models also employ a modified version of the above three CNN architectures.Using the RIM-ONE dataset,the attention U-Net with the ResNet50 model as the encoder backbone,achieved the best accuracy of 99.58%in segmenting OD.The Inception-v3 model had the highest accuracy of 98.79%for glaucoma classification among the evaluated segmentation,followed by the modified classification architectures. | Thisara Shyamalee Dulani Meedeniya | 2022 | Machine Intelligence Research2022，19，6： | 1 |
| 14 | Machine Learning for Cataract Classification/Grading on Ophthalmic Imaging Modalities:A Survey显示文摘Cataracts are the leading cause of visual impairment and blindness globally.Over the years,researchers have achieved significant progress in developing state-of-the-art machine learning techniques for automatic cataract classification and grading,aiming to prevent cataracts early and improve clinicians′diagnosis efficiency.This survey provides a comprehensive survey of recent advances in machine learning techniques for cataract classification/grading based on ophthalmic images.We summarize existing literature from two research directions:conventional machine learning methods and deep learning methods.This survey also provides insights into existing works of both merits and limitations.In addition,we discuss several challenges of automatic cataract classification/grading based on machine learning techniques and present possible solutions to these challenges for future research. | Xiao-Qing Zhang Yan Hu Zun-Jie Xiao Jian-Sheng Fang Risa Higashita Jiang Liu | 2022 | Machine Intelligence Research2022，19，3： | 1 |
| 15 | Towards Interpretable Defense Against Adversarial Attacks via Causal Inference显示文摘Deep learning-based models are vulnerable to adversarial attacks. Defense against adversarial attacks is essential for sensitive and safety-critical scenarios. However, deep learning methods still lack effective and efficient defense mechanisms against adversarial attacks. Most of the existing methods are just stopgaps for specific adversarial samples. The main obstacle is that how adversarial samples fool the deep learning models is still unclear. The underlying working mechanism of adversarial samples has not been well explored, and it is the bottleneck of adversarial attack defense. In this paper, we build a causal model to interpret the generation and performance of adversarial samples. The self-attention/transformer is adopted as a powerful tool in this causal model. Compared to existing methods, causality enables us to analyze adversarial samples more naturally and intrinsically. Based on this causal model, the working mechanism of adversarial samples is revealed, and instructive analysis is provided. Then, we propose simple and effective adversarial sample detection and recognition methods according to the revealed working mechanism. The causal insights enable us to detect and recognize adversarial samples without any extra model or training. Extensive experiments are conducted to demonstrate the effectiveness of the proposed methods. Our methods outperform the state-of-the-art defense methods under various adversarial attacks. | Min Ren Yun-Long Wang Zhao-Feng He | 2022 | Machine Intelligence Research2022，19，3： | 1 |
| 16 | TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization显示文摘Action recognition and localization in untrimmed videos is important for many applications and have attracted a lot of attention. Since full supervision with frame-level annotation places an overwhelming burden on manual labeling effort, learning with weak video-level supervision becomes a potential solution. In this paper, we propose a novel weakly supervised framework to recognize actions and locate the corresponding frames in untrimmed videos simultaneously. Considering that there are abundant trimmed videos publicly available and well-segmented with semantic descriptions, the instructive knowledge learned on trimmed videos can be fully leveraged to analyze untrimmed videos. We present an effective knowledge transfer strategy based on inter-class semantic relevance. We also take advantage of the self-attention mechanism to obtain a compact video representation, such that the influence of background frames can be effectively eliminated. A learning architecture is designed with twin networks for trimmed and untrimmed videos, to facilitate transferable self-attentive representation learning. Extensive experiments are conducted on three untrimmed benchmark datasets (i.e., THUMOS14, ActivityNet1.3, and MEXaction2), and the experimental results clearly corroborate the efficacy of our method. It is especially encouraging to see that the proposed weakly supervised method even achieves comparable results to some fully supervised methods. | Xiao-Yu Zhang Hai-Chao Shi Chang-Sheng Li Li-Xin Duan | 2022 | Machine Intelligence Research2022，19，3： | 1 |
| 17 | Dense Face Network:A Dense Face Detector Based on Global Context and Visual Attention Mechanism显示文摘Face detection has achieved tremendous strides thanks to convolutional neural networks. However, dense face detection remains an open challenge due to large face scale variation, tiny faces, and serious occlusion. This paper presents a robust, dense face detector using global context and visual attention mechanisms which can significantly improve detection accuracy. Specifically, a global context fusion module with top-down feedback is proposed to improve the ability to identify tiny faces. Moreover, a visual attention mechanism is employed to solve the problem of occlusion. Experimental results on the public face datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method. | Lin Song Jin-Fu Yang Qing-Zhen Shang Ming-Ai Li | 2022 | Machine Intelligence Research2022，19，3： | 1 |
| 18 | Brain-inspired Intelligent Robotics:Theoretical Analysis and Systematic Application显示文摘Traditional joint-link robots have been widely used in production lines because of their high precision for single tasks.With the development of the manufacturing and service industries,the requirement for the comprehensive performance of robotics is growing.Numerous types of bio-inspired robotics have been investigated to realize human-like motion control and manipulation.A study route from inner mechanisms to external structures is proposed to imitate humans and animals better.With this idea,a brain-inspired intelligent robotic system is constructed that contains visual cognition,decision-making,motion control,and musculoskeletal structures.This paper reviews cutting-edge research in brain-inspired visual cognition,decision-making,motion control,and musculoskeletal systems.Two software systems and a corresponding hardware system are established,aiming at the verification and applications of next-generationbrain-inspired musculoskeletal robots. | Hong Qiao Ya-Xiong Wu Shan-Lin Zhong Pei-Jie Yin Jia-Hao Chen | 2023 | Machine Intelligence Research2023，20，1： | 1 |
| 19 | Federated Learning with Privacy-preserving and Model IP-right-protection显示文摘In the past decades,artificial intelligence(AI)has achieved unprecedented success,where statistical models become the central entity in AI.However,the centralized training and inference paradigm for building and using these models is facing more and more privacy and legal challenges.To bridge the gap between data privacy and the need for data fusion,an emerging AI paradigm feder-ated learning(FL)has emerged as an approach for solving data silos and data privacy problems.Based on secure distributed AI,feder-ated learning emphasizes data security throughout the lifecycle,which includes the following steps:data preprocessing,training,evalu-ation,and deployments.FL keeps data security by using methods,such as secure multi-party computation(MPC),differential privacy,and hardware solutions,to build and use distributed multiple-party machine-learning systems and statistical models over different data sources.Besides data privacy concerns,we argue that the concept of“model”matters,when developing and deploying federated models,they are easy to expose to various kinds of risks including plagiarism,illegal copy,and misuse.To address these issues,we introduce FedIPR,a novel ownership verification scheme,by embedding watermarks into FL models to verify the ownership of FL models and protect model intellectual property rights(IPR or IP-right for short).While security is at the core of FL,there are still many articles re-ferred to distributed machine learning with no security guarantee as“federated learning”,which are not satisfied with the FL definition supposed to be.To this end,in this paper,we reiterate the concept of federated learning and propose secure federated learning(SFL),where the ultimate goal is to build trustworthy and safe AI with strong privacy-preserving and IP-right-preserving.We provide a com-prehensive overview of existing works,including threats,attacks,and defenses in each phase of SFL from the lifecycle perspective. | Qiang Yang Anbu Huang Lixin Fan Chee Seng Chan Jian Han Lim Kam Woh Ng Ding Sheng Ong Bowen Li | 2023 | Machine Intelligence Research2023，20，1： | 1 |
| 20 | Transmission Line Insulator Defect Detection Based on Swin Transformer and Context显示文摘Insulators are important components of power transmission lines.Once a failure occurs,it may cause a large-scale blackout and other hidden dangers.Due to the large image size and complex background,detecting small defect objects is a challenge.We make improvements based on the two-stage network Faster R-convolutional neural networks(CNN).First,we use a hierarchical Swin Transformer with shifted windows as the feature extraction network,instead of ResNet,to extract more discriminative features,and then design the deformable receptive field block to encode global and local context information,which is utilized to capture key clues for detecting objects in complex backgrounds.Finally,the filling data augmentation method is proposed for the problem of insufficient defects and more images of insulator defects under different backgrounds are added to the training set to improve the robustness of the model.As a result,the recall increases from 89.5%to 92.1%,and the average precision increases from 81.0%to 87.1%.To further prove the superiority of the proposed algorithm,we also tested the model on the public data set Pascal visual object classes(VOC),which also yields outstanding results. | Yu Xi Ke Zhou Ling-Wen Meng Bo Chen Hao-Min Chen Jing-Yi Zhang | 2023 | Machine Intelligence Research2023，20，5： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员