检索结果-内蒙古大学图书馆

SAPT: Saliency Augmentation and Unsupervised Pre-trained Model Fusion for few-shot object detection

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2024年第11期96卷 747-762页

作者： Liao, Yujun Wu, Yan Mo, Yujian He, Yufei Hu, Yinghao Zhao, Junqiao Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China Tongji Univ Inst Intelligent Vehicle Shanghai 201804 Peoples R China

object detection algorithms require a large amount of annotated data for training and optimization, which can be time-consuming, expensive, and limit model robustness and generalization. The natural world has a diverse range of target categories, and privacy and security concerns make obtaining accurate data a challenge. Researchers are developing new methods and technologies to achieve fast and accurate object detection with minimal annotations. Recent few-shot object detection methods have employed semi-supervised learning, domain adaptation, and meta-learning techniques to enable efficient knowledge transfer from base to new categories. However, these methods have not directly addressed the primary challenge of few-shot object detection, which is the lack of sufficient labeled data for new categories. This study introduces SAPT, a few-shot object detection method based on saliency data augmentation and unsupervised pre-training model fusion. In the data preprocessing stage, SAPT selects two images for detection and crops an object of the same category from each based on ground truth labels. The maximum and minimum salient circular regions of the two cropped objects are detected and blended to generate an augmented image that expands the training dataset. In the testing stage, the output of the supervised few-shot object detection and unsupervised pre-training models are integrated and mined to generate dynamic positive and negative support images, improving the detector's accuracy. SAPT optimizes the detection process by addressing issues of insufficient data for unknown class labels and low detection accuracy in open-world scenarios. Extensive experiments on benchmark datasets MS COCO and PASCAL VOC demonstrate SAPT's superior performance compared to existing few-shot object detection methods.

关键词： few-shot object detection Saliency detection Data augmentation Unsupervised pre-training

来源：评论

学校读者我要写书评

暂无评论

A Neuroinspired Contrast Mechanism enables few-shot object detection

引用

PATTERN RECOGNITION 2024年 156卷

作者： Yang, Lingxiao Chen, Dapeng Chen, Yifei Peng, Wei Xie, Xiaohua Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China Huawei Technol Shenzhen Peoples R China

Deep learning-based object detectors often demand abundant annotated data for training. However, in practice, only limited training data are available, making few-shot object detection (FSOD) an attractive research topic. Existing two-stage proposal-based Faster R-CNN detectors for FSOD struggle to match the performance of models trained on large datasets. We argue that detectors trained with limited samples cannot establish robust comparison-based relationships. Additionally, FSOD methods only explore these relationships during the training phase. To address these issues, we draw inspiration from neuroscience studies and propose Residual Contrast Faster R-CNN (RcFRCN). RcFRCN incorporates two novel customized contrast blocks: a Residual Spatial Contrast Block and a Residual Proposal Contrast Block. These blocks capture cross-spatial and cross-proposal contrast information, enhancing both training and testing phases. We conduct comprehensive experiments on two FSOD benchmarks: PASCAL VOC and MS-COCO. Our RcFRCN achieves a mAP of 21.9 under a 30-shot setting on MS-COCO. It also achieves AP scores of 69.1, 55.8, and 64.0 under 10-shot settings of different splits on PASCAL VOC, respectively. Moreover, we apply RcFRCN on remote sensing and use our contrast blocks for open-vocabulary detection. Experiment results on these tasks also demonstrate the robustness and generalization ability of our methods.

关键词： few-shot object detection Contrast Blocks Faster R-CNN Perceptual Learning

来源：评论

学校读者我要写书评

暂无评论

FSODv2: A Deep Calibrated few-shot object detection Network

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2024年第9期132卷 3566-3585页

作者： Fan, Qi Zhuo, Wei Tang, Chi-Keung Tai, Yu-Wing Nanjing Univ State Key Lab Novel Software Technol Nanjing Peoples R China Nanjing Univ Sch Intelligence Sci & Technol Suzhou Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Clear Water Bay Hong Kong Peoples R China Dartmouth Coll Comp Sci Dept Hanover NH 03755 USA

Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel few-shot object detection network (FSODv2) in this paper that aims to detect objects from previously unseen categories using only a few annotated examples. Attention RPN, Multi-Relation Detector, and Contrastive Training strategy are central to our method (Fan et al., in: CVPR, 2020), which exploit similarity between few shot support set and query set to detect novel objects while suppressing false detection in the background. We also contribute a new dataset, FSOD-1k, which contains 1000 categories of various objects with high-quality annotations to train our network. To the best of our knowledge, this is one of the first datasets designed for few-shot object detection. This paper improves our FSOD model through well-designed model calibration in three areas: (1) we propose an improved FPN with multi-scale support inputs to calibrate the multi-scale support-query feature matching by exploiting multi-scale features from the same support image with different input scales;(2) we introduce a support classification supervision branch to calibrate the support feature supervision, aligning to the query feature training supervision;(3) we propose backbone calibration to preserve prior knowledge while alleviating backbone bias toward base classes by employing classification dataset to help our model calibration procedure, where such dataset has previously only been used for pre-training in other related works. Besides, we propose a Fast Attention RPN to improve evaluation speed and save computational memory during inference. Once trained, our few-shot network can detect objects from previously unseen categories without further training or fine-tuning, resulting in new state-of-the-art performance on different datasets in the few-shot setting. Our method is general in scope and has numerous potenti

关键词： few-shot object detection Attention Multi-relation Dataset Benchmark

来源：评论

学校读者我要写书评

暂无评论

Low-light few-shot object detection via curve contrast enhancement and flow-encoder-based variational autoencoder

引用

Neural Computing and Applications 2025年第10期37卷 7261-7278页

作者： Jiang, Zetao Jin, Xin Kang, Junjie The Key Laboratory of image and graphic intelligent processing Guilin University of Electronic Technology Guangxi Guilin541004 China Wuhan Service Department Sinopec Shared Services.LTD.Nanjing Branch Jiangsu Nanjing210018 China Co. LTD Geely Group Zhejiang Ningbo315336 China

Aiming at the problem of insufficient samples in low-light object detection in some environments, a low-light few-shot object detection method based on curve contrast enhancement and flow-encoder-based variational autoencoder (CCEFVAE) is proposed. Our approach involves designing a CCE module to enhance the detailed features and contrast of low-light images by deriving a relationship expression between the enhanced image and the low-light image through the recursive relationship of high-order curves. The lumination estimation module in the CCE module estimates the parameters of the expression to calculate the pixel values of the enhanced image. Moreover, we propose an FVAE module to improve the decoupling of support features by combining the flow model encoder with the variational autoencoder, facilitating subsequent feature aggregation and classification. To ensure the consistency of the loss function of the flow model with the few-shot object detection loss, we design a negative Jacobian determinant transformation function. This enables direct addition of the two losses, allowing for unified optimization. Experimental results demonstrate that our proposed algorithm outperforms mainstream few-shot object detection models by an average of 13.1–23% in average after training on the low-light dataset (ExDark), and shows an average improvement of 5.8% compared to the state-of-the-art (SOTA) few-shot object detection model VFA. When trained on the normal lighting dataset (PASCAL VOC), the proposed algorithm exhibits a 1.7% improvement in average compared to VFA. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Curve contrast enhancement few-shot object detection Flow-encoder-based variational autoencoder Low-light environment

来源：评论

学校读者我要写书评

暂无评论

Text generation and multi-modal knowledge transfer for few-shot object detection

引用

PATTERN RECOGNITION 2025年 161卷

作者： Du, Yaoyang Liu, Fang Jiao, Licheng Li, Shuo Hao, Zehua Li, Pengfang Wang, Jiahao Wang, Hao Liu, Xu Minist Educ Key Lab Intelligent Percept & Image Understanding Beijing Peoples R China Int Res Ctr Intelligent Percept & Computat Beijing Peoples R China Joint Int Res Lab Intelligent Percept & Computat Beijing Peoples R China Xidian Univ Sch Artificial Intelligent Xian 710071 Shaanxi Peoples R China

The challenge of detecting novel categories with limited annotated samples for learning is referred to as few shot object detection (FSOD). Due to the scarcity of data, networks struggle to learn robust features that effectively represent object categories from limited samples. Currently, most methods addressing FSOD tasks rely solely on a single modality in network design, overlooking the advanced semantic relationships between categories and their descriptions. We propose a method named Text Generation and Multi-Modal Knowledge Transfer for few-shot object detection (MMKT). This approach employs a Text Prompt Descriptors Generator (TPDG) to generate prompts tailored to specific categories, reducing the reliance on particular knowledge sources observed in previous methods. To better understand the relationship between text-based descriptions and visual features in a shared space, we develop an Image-Text Matching module to establish correlations between textual and visual features. Experiments demonstrate the effectiveness of MMKT method.

关键词： few-shot learning few-shot object detection Multi-modal

来源：评论

学校读者我要写书评

暂无评论

Multiple knowledge embedding for few-shot object detection

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2023年第5期17卷 2231-2240页

作者： Gong, Xiaolin Cai, Youpeng Wang, Jian Tianjin Univ Sch Microelect Tianjin 300072 Peoples R China Tianjin Univ Tianjin Key Lab Imaging & Sensing Microelect Techn Tianjin 300072 Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

In the problem of few-shot object detection, class prototype knowledge in previous works is not be fully refined and utilized due to lack of instances. We noticed that the application of the output features of the RoI pooling layer has a great influence on the grasp of the prototype features, which motivates us to focus on how to reuse them. Therefore, we propose a multiple knowledge embedding network, which gets improvement in three places in the fine-tuning stage. Introducing attention mechanism to strengthen feature extraction, Up-CoTNet is used to replace the 3x3 convolution in Resnet101. Feature enhancement module is added to enforce the common object reasoning for the output of RoI pooling layer. Then, we propose a contrastive learning branch to grasp the information encoded between different feature regions. Experiments on PASCAL VOC and MS COCO datasets show that our model significantly raises the performance by 1.3% (+0.5AP) in average compared with previous methods.

关键词： few-shot object detection Multiple knowledge embedding Feature enhancement Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A broader study of cross-domain few-shot object detection

引用

APPLIED INTELLIGENCE 2023年第23期53卷 29465-29485页

作者： Sa, Liangbing Yu, Chongchong Hong, Zhaorui Zheng, Tong Liu, Sihan Beijing Technol & Business Univ Beijing 100048 Peoples R China

Latest studies on few-shot object detection (FSOD) mainly focuses on achieving better performance in novel class through few-shot fine-tuning. This approach is based on the large amount of annotated data in base class to pre-train models. However, in many scenarios it is difficult or impossible to gather substantial data for the base class of the same domain as the novel class. This leads to the cross-domain few-shot object detection problem. Existing research on scenarios of cross-domain few-shot object detection is only limited to generalization where the base and novel class are from highly similar domains of natural images (i.e., from COCO to VOC). In this respect, we propose the Broader Study of Cross-Domain few-shot object detection (BSCD-FSOD) benchmark. The generalization is thus possible both from a natural image domain to another, for instance from COCO to ExDark (low-light images) and from a natural image domain to a dissimilar one, for instance from COCO to Clipar1k (artistic media images), to NEU-DET (industrial defect images) or to DOTA (satellite images). We have performed extensive experiments on the proposed benchmark to evaluate state-of-art transfer learning approaches. Research results show that, previous state-of-art methods are no longer state-of-art. Pretraining models on COCO instead of VOC can help them learn a wider feature distribution. The less the domains are similar to those of natural images, the more trainable network components fine-tuning thus requires. The performance of all methods is correlated to both the target domain and the degree of similarity between source and target domain. The results we get show the diversity of data distribution and validate the value of our benchmark, which will offer guidance for future researches.

关键词： few-shot object detection Cross-domain Transfer learning Benchmark

来源：评论

学校读者我要写书评

暂无评论

RecFRCN: few-shot object detection With Recalibrated Faster R-CNN

引用

IEEE ACCESS 2023年 11卷 121109-121117页

作者： Zhang, Youyou Lu, Tongwei Wuhan Inst Technol Sch Comp Sci & Engn Wuhan 430205 Peoples R China Wuhan Inst Technol Hubei Key Lab Intelligent Robot Wuhan 430205 Peoples R China

Currently, Faster R-CNN serves as the fundamental detection framework in the majority of few-shot object detection algorithms. However, due to limited samples per class, the Faster R-CNN's classification branch faces limitations in capturing specific features for each class in a few-shot scenario, leading to a bias towards false positives. These high-score false positives subsequently result in poor classification task performance. To address this issue, we propose a novel approach, named Recalibrated Faster R-CNN, which recalibrates the categories of regression boxes. Specifically, we introduce a new classification network (Rec-Net) for Faster R-CNN's Box Predictor, including a feature extractor, a feature enhancement block (FEB), an ROI Pooling layer, and a local descriptor classifier (LDC). The feature extractor extracts features from input images, while FEB enhances these features. The ROI Pooling layer projects prediction boxes from Faster R-CNN onto a fixed-size feature map. LDC not only obtains the optimal depth local descriptors from ROI features for image-to-class measurement but also, in the few-shot setting, uses local representation as natural data enhancement for increased efficiency, ultimately enhancing the original classification scores. Our experimental results demonstrate strong performance across several benchmark tests.

关键词： few-shot object detection metric learning object detection

来源：评论

学校读者我要写书评

暂无评论

Efficient few-shot object detection via Knowledge Inheritance

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 321-334页

作者： Yang, Ze Zhang, Chi Li, Ruibo Xu, Yi Lin, Guosheng Nanyang Technol Univ NTU Sch Comp Sci & Engn Singapore 639798 Singapore OPPO US Res Ctr Inno Peak Technol Inc Palo Alto CA 94303 USA

few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency issues, e.g., high computational complexity and slow adaptation speed. Notably, efficiency has become an increasingly important evaluation metric for few-shot techniques due to an emerging trend toward embedded AI. To this end, we present an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods. Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed. Within the KI initializer, we propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights. Finally, our approach not only achieves the SOTA results across three public benchmarks, i.e., PASCAL VOC, COCO and LVIS, but also exhibits high efficiency with $1.8-100\times $ faster adaptation speed against the other methods on COCO/LVIS benchmark during few-shot transfer. To our best knowledge, this is the first work to consider the efficiency problem in FSOD. We hope to motivate a trend toward powerful yet efficient few-shot technique development.

关键词： few-shot object detection transfer learning incremental learning meta learning

来源：评论

学校读者我要写书评

暂无评论

few-shot object detection in Remote Sensing Images via Data Clearing and Stationary Meta-Learning

引用

SENSORS 2024年第12期24卷 3882页

作者： Yang, Zijiu Guan, Wenbin Xiao, Luyang Chen, Honggang Sichuan Univ Coll Elect & Informat Engn Chengdu 610065 Peoples R China

Nowadays, the focus on few-shot object detection (FSOD) is fueled by limited remote sensing data availability. In view of various challenges posed by remote sensing images (RSIs) and FSOD, we propose a meta-learning-based Balanced few-shot object Detector (B-FSDet), built upon YOLOv9 (GELAN-C version). Firstly, addressing the problem of incompletely annotated objects that potentially breaks the balance of the few-shot principle, we propose a straightforward yet efficient data clearing strategy, which ensures balanced input of each category. Additionally, considering the significant variance fluctuations in output feature vectors from the support set that lead to reduced effectiveness in accurately representing object information for each class, we propose a stationary feature extraction module and corresponding stationary and fast prediction method, forming a stationary meta-learning mode. In the end, in consideration of the issue of minimal inter-class differences in RSIs, we propose inter-class discrimination support loss based on the stationary meta-learning mode to ensure the information provided for each class from the support set is balanced and easier to distinguish. Our proposed detector's performance is evaluated on the DIOR and NWPU VHR-10.v2 datasets, and comparative analysis with state-of-the-art detectors reveals promising performance.

关键词： few-shot object detection remote sensing images meta-learning incompletely annotated objects

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：