相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Proceedings Paper
Computer Science, Artificial Intelligence
Yinpeng Chen et al.
Summary: Mobile-Former is a parallel design of MobileNet and transformer with a two-way bridge, combining the advantages of both models for efficient computation and enhanced representation power across image classification and object detection tasks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Dingheng Wang et al.
Summary: This research introduces a novel nonlinear tensor train (NTT) format by studying various tensor decomposition methods, which compensates for the accuracy loss that normal tensor train (TT) cannot provide by embedding additional nonlinear activation functions in sequenced contractions and convolutions. Experimental results demonstrate that the compressed DNNs in the NTT format can maintain accuracy on multiple datasets.
Article
Computer Science, Artificial Intelligence
Wenxiao Wang et al.
Summary: As deep CNNs become larger, deploying them on mobile devices with limited resources becomes more challenging. Filter-level pruning is a popular method to compress deep models for mobile deployment, but it still faces issues such as high redundancy and sub-optimality.
Review
Computer Science, Artificial Intelligence
Chunying Wang et al.
Summary: Hyperspectral imaging is a non-destructive, nonpolluting, and fast technology used for agricultural information acquisition and quality attribute detection. Deep learning techniques have significantly enhanced the performance of hyperspectral image analysis, particularly in applications such as predicting ripeness and components of agricultural products, and detecting plant diseases.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Zhao Zhong et al.
Summary: In this paper, the authors propose BlockQNN, a block-wise network generation pipeline that automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The approach outperformed hand-crafted networks on image classification tasks and showed strong generalizability across datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Donghyun Lee et al.
Summary: This article introduces a training framework for three-dimensional convolutional neural networks called QTTNet, which combines tensor train decomposition and data quantization to further shrink the model size and reduce memory and time costs. Experimental results demonstrate the effectiveness and competitiveness of this method in compressing 3D object and video recognition models.
Proceedings Paper
Computer Science, Artificial Intelligence
Ziwei Wang et al.
Summary: This paper introduces a generalizable mixed-precision quantization method, which significantly reduces search cost on large-scale datasets without performance degradation. By accurately locating network attribution across different data distributions, the method achieves a competitive accuracy-complexity trade-off.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Lewei Yao et al.
Summary: This paper introduces a novel knowledge distillation strategy for object detection, incorporating feature imitation and contrastive distillation techniques. The method outperforms existing detection KD techniques for both homogeneous and heterogeneous student-teacher pairs.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ge-Peng Ji et al.
Summary: The paper introduces a novel framework called FSNet, which utilizes a relational cross-attention module and bidirectional purification module to achieve bidirectional message passing and improve model robustness. By performing cross-modal feature-passing before fusion and decoding, the model demonstrates robustness to various challenging scenarios in video object segmentation.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Hao Tang et al.
Summary: This work proposes a new framework for few-shot medical image segmentation based on prototypical networks, achieving substantial improvement over state-of-the-art methods in experiments by designing a context relation encoder and a recurrent mask refinement module.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Boyu Chen et al.
Summary: BN-NAS is a method for accelerating neural architecture search using Batch Normalization, which predicts subnet performance and improves training efficiency by training only BN parameters.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Neel Dey et al.
Summary: Deformable templates are crucial for various medical image processing tasks, but traditional methods often produce blurry or anatomically implausible templates. This study introduces an adversarial game approach to enhance the realism of moved templates, resulting in templates with better specificity to attributes and improved sharpness and centrality, enabling more accurate population modeling and anatomical delineation for biomedical analysis.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yunyao Mao et al.
Summary: This study introduces a unified framework that integrates transductive and inductive learning for accurate and robust video object segmentation by exploiting the complementarity between the two. The approach consists of two functional branches, one for aggregating spatio-temporal cues and the other for obtaining discriminative target information.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Sheng Zhou et al.
Summary: Knowledge Distillation (KD) aims to transfer knowledge from a teacher network to a student network, with individual and relational knowledge being crucial components, but existing methods often overlook the inherent correlations between them.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Minghao Chen et al.
Summary: AutoFormer is a novel one-shot architecture search framework dedicated to vision transformer search. It outperforms recent models like ViT and DeiT, achieving good accuracy on ImageNet by training a supernet and generating comparable subnets.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Manish Sharma et al.
Summary: Convolutional auto-encoders (CAEs) are often over-parameterized when trained with small or moderate-sized datasets, leading to decreased performance.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zixiao Zhang et al.
Summary: The study introduces an improved backbone network, MHSA-Darknet, for object detection, utilizing multi-head self-attention and a weighted bi-directional feature pyramid network for feature fusion. Additional techniques like TTA and WBF are employed to enhance accuracy and robustness, leading to significant performance improvements over state-of-the-art detectors in the VisDrone-DET 2021 challenge.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Naoya Takahashi et al.
Summary: This paper introduces a novel CNN architecture called D3Net, which emphasizes the importance of simultaneously modeling different resolutions using multidilated convolution with varying dilation factors in a single layer. By combining multidilated convolution with DenseNet architecture, D3Net achieves multiresolution learning with an exponentially growing receptive field in almost all layers, outperforming state-of-the-art methods in image semantic segmentation and audio source separation tasks.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yehui Tang et al.
Summary: The proposed approach in this paper dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the method is verified on several benchmarks, showing better performance in terms of both accuracy and computational cost compared to state-of-the-art methods. This new paradigm maximally excavates redundancy in the network architecture.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yixing Xu et al.
Summary: This study introduces a relative performance prediction method for neural architecture search, which can find better-performing architectures while saving computational costs. Experimental results show that sampling a small number of neural architectures on the NAS-Bench-101 dataset is sufficient to learn an accurate architecture performance predictor.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Kohei Yamamoto
Summary: The proposed learnable companding quantization (LCQ) method optimizes model weights and companding functions to control non-uniform quantization, along with a new weight normalization technique. Experimental results show that LCQ outperforms conventional methods in image classification and object detection tasks, narrowing the gap between quantization and full-precision models.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Meng Ye et al.
Summary: Our study introduces a deep learning-based unsupervised method for in vivo motion tracking on t-MRI images, which utilizes temporal information for reasonable estimations on spatiotemporal motion fields, providing a useful solution for motion tracking and image registration in dynamic medical imaging.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Anjith George et al.
Summary: This study presents a new framework for facial presentation attack detection using RGB and depth channels together with a novel loss function. By optimizing the cross-modal focal loss function, it effectively improves the robustness of PAD systems. Extensive evaluations on publicly available datasets demonstrate the effectiveness of the proposed approach.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhizhong Huang et al.
Summary: This paper proposes a unified, multi-task framework MTLFace to handle age-invariant identity-related representation and face synthesis, by decomposing face features using an attention mechanism, removing age correlation through multi-task training and continuous domain adaption, introducing an identity conditional module for identity-level face synthesis, and achieving superior performance in experiments.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Changlin Li et al.
Summary: The study introduces a dynamic thinning network mechanism called DS-Net, aiming to dynamically adjust the number of filters in the network at test time to achieve hardware efficiency while maintaining static storage to prevent extra burden. Dynamic inference is achieved through a double-headed dynamic gate, with a two-stage training scheme proposed for the generality of candidate architectures and fairness of the gate.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhaohui Yang et al.
Summary: This paper proposes an hourglass-inspired approach (HourNAS) for extremely fast Neural Architecture Search (NAS) by identifying vital blocks and making them the priority in the architecture search. Experimental results show that HourNAS can search for a high-performing architecture in a very short period of time.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Tianyi Zhao et al.
Summary: The study proposes a holistic segmentation-mesh-classification network (SMCN) for distinguishing pancreatic ductal adenocarcinoma (PDAC) from nonPDAC masses, utilizing both image appearance and the 3D organ-mass geometry relationship. SMCN combines anatomical structure and semantic detection to provide patient-level diagnosis, achieving improved mass segmentation and detection accuracy compared to the baseline method, and comparable results to expert radiologists and multimodality testing for clinical management.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jinguo Zhu et al.
Summary: This paper introduces a novel knowledge distillation method, Complementary Relation Contrastive Distillation (CRCD), which transfers structural knowledge from teacher to student using anchor points. By maximizing mutual information between anchor-teacher and anchor-student relations, it effectively distills sample representations and inter-sample relations. Experimental results on various benchmarks demonstrate the effectiveness of the proposed CRCD.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ryan Razani et al.
Summary: Neural network models are resource intensive and difficult to deploy on devices with limited resources. Low bit quantization such as binary and ternary quantization can alleviate this issue, with ternary quantization being more accurate. Mixed quantized models allow a trade-off between accuracy and memory footprint.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Arthur J. Redfern et al.
Summary: This paper introduces a CNN with fully binary 2D convolution operations, achieving 71.24% top 1 accuracy on the ImageNet validation set. The network structure is derived from a proof showing that binary neural networks are universal function approximators, and uses implementation strategies optimized for binary operands.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Review
Computer Science, Theory & Methods
Laith Alzubaidi et al.
Summary: Deep learning has become the gold standard in the machine learning community, widely used in various domains and capable of learning massive data. Through a comprehensive survey, a better understanding of the most important aspects of deep learning is provided.
JOURNAL OF BIG DATA
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Nima Aghli et al.
Summary: Model compression is crucial for deep neural networks, with popular methods like weight pruning not suitable for complex networks like ResNets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Article
Computer Science, Artificial Intelligence
Prachi Punyani et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Article
Computer Science, Artificial Intelligence
Tejalal Choudhary et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Article
Computer Science, Artificial Intelligence
Abhijit Guha Roy et al.
MEDICAL IMAGE ANALYSIS
(2020)
Article
Computer Science, Information Systems
Laith Alzubaidi et al.
Article
Computer Science, Artificial Intelligence
Asifullah Khan et al.
ARTIFICIAL INTELLIGENCE REVIEW
(2020)
Article
Computer Science, Artificial Intelligence
Jinmian Ye et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Yudong Wu et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Qianru Zhang et al.
Article
Computer Science, Hardware & Architecture
Duy Thanh Nguyen et al.
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
(2019)
Article
Computer Science, Information Systems
Lianqiang Li et al.
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
(2019)
Article
Computer Science, Artificial Intelligence
Haisong Ding et al.
PATTERN RECOGNITION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhichao Lu et al.
PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Ziwei Wang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Hardware & Architecture
Weizhe Hua et al.
MICRO'52: THE 52ND ANNUAL IEEE/ACM INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE
(2019)
Article
Computer Science, Information Systems
Zongyue Wang et al.
Article
Computer Science, Artificial Intelligence
Jiuxiang Gu et al.
PATTERN RECOGNITION
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Peisong Wang et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Dongyoon Han et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Peisong Wang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Hardware & Architecture
Sajid Anwar et al.
ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Yihui He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Xiangyu Zhang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2016)
Article
Robotics
Suraj Srinivas et al.
FRONTIERS IN ROBOTICS AND AI
(2016)
Article
Computer Science, Artificial Intelligence
Kaiming He et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Article
Computer Science, Theory & Methods
Nesli Erdogmus et al.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2014)
Article
Engineering, Electrical & Electronic
Kyong Ho Lee et al.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2013)
Article
Computer Science, Artificial Intelligence
J. R. R. Uijlings et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2013)
Article
Computer Science, Artificial Intelligence
Herve Jegou et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2011)
Article
Mathematics, Applied
I. V. Oseledets
SIAM JOURNAL ON SCIENTIFIC COMPUTING
(2011)
Article
Multidisciplinary Sciences
G. E. Hinton et al.
