检索结果-内蒙古大学图书馆

DP-DDCL: A discriminative prototype with dual decoupled contrast learning method for few-shot object detection

KNOWLEDGE-BASED SYSTEMS 2024年 297卷

作者： Guo, Yinsai Ma, Liyan Luo, Xiangfeng Xie, Shaorong Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China

few -shot object detection (FSOD) can effectively improve object detection performance with limited training data, attracting increasing interest from researchers. Due to the limited sample size, there is often a large variance in the learned features, resulting in deviating from the class center and being confused with other classes. People are often able to accurately identify few -shot objects based on discriminative information. Motivated by it, we propose a discriminative prototype with dual decoupled contrast learning (DP-DDCL) method to address the issue of limited training data in FSOD. By introducing domain knowledge comprising the CLIP and attribute knowledge graph to obtain explicit and implicit semantic and visual information, we construct a novel discriminative prototype that enhances the representation of different classes (especially few -shot samples). Simultaneously, dual decoupled contrast learning consists of the decoupled of positive and negative samples, and the decoupled of discriminative prototype and instance contrast learning is proposed. It makes samples of the same class cluster around their respective class prototype while maintaining a clear semantic boundary between different classes. Extensive experiments demonstrate the efficacy of our method, surpassing the current state-of-the-art in any -shot and all -data splits, with maximum performance gains of up to +9.15% on the standard PASCAL VOC benchmark and +2.5% on the challenging COCO benchmark.

关键词： few-shot object detection Discriminative prototype Domain knowledge Discriminative multimodal cross-attention Dual decoupled contrast learning

来源：评论

学校读者我要写书评

暂无评论

MSO-DETR: Metric space optimization for few-shot object detection

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1515-1533页

作者： Haifeng Sima Manyang Wang Lanlan Liu Yudong Zhang Junding Sun School of Computer Science and Technology Henan Polytechnic UniversityJiaozuoChina Institute of Quantitative Remote Sensing and Smart Agriculture Henan Polytechnic UniversityJiaozuoChina Faculty of Arts and Law Henan Polytechnic UniversityJiaozuoChina School of Computing and Mathematical Sciences University of LeicesterLeicesterUK

In the metric-based meta-learning detection model,the distribution of training samples in the metric space has great influence on the detection performance,and this influence is usually ignored by traditional *** addition,the design of metric space might be interfered with by the background noise of training *** tackle these issues,we propose a metric space optimisation method based on hyperbolic geometry attention and class-agnostic activation ***,the geometric properties of hyperbolic spaces to establish a structured metric space are used.A variety of feature samples of different classes are embedded into the hyperbolic space with extremely low *** metric space is more suitable for representing tree-like structures between categories for image scene ***,a novel similarity measure function based on Poincarédistance is proposed to evaluate the distance of various types of objects in the feature *** addition,the class-agnostic activation maps(CCAMs)are employed to re-calibrate the weight of foreground feature information and suppress background ***,the decoder processes the high-level feature information as the decoding of the query object and detects objects by predicting their locations and corresponding task *** evaluation is conducted on Pascal VOC and MS COCO *** experiment results show that the effectiveness of the authors’method surpasses the performance baseline of the excellent few-shot detection models.

关键词： few-shot object detection hyperbolic space meta-learning metric space

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

CLFM: few-shot object detection via Low-Resource Contrastive Learning and Fisher Matrix Updating for Overcoming Catastrophic Forgetting

引用

IEEE ACCESS 2022年 10卷 115307-115321页

作者： Wang, Meng Wang, Qiang Liu, Haipeng Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming Yunnan Peoples R China

few-shot object detection (FSOD) aims to efficiently detect novel instances by model transferring using a few novel-class samples after the base-class samples are pre-trained. However, catastrophic forgetting occurs when FSOD transfers to the novel-classes, making the transferred model unable to accurately detect base and novel class instances simultaneously. Thus, this paper attempts to extend the general elastic weight curing (EWC) to the field of few-shot transfer detection. An online soft constraint is applied by evaluating the Fisher information matrix of inner-batch samples based on mean squared error (MSE) metric to constrain or encourage model parameters transferring. Also, a momentum update based inter-batch storage mechanism is proposed to alleviate the memory strain caused by the previously applied contrastive learning modules when performing numerous contrastive encoding procedures. Finally, a compact heterogeneous decoupled-head is formulated to remove information entanglement between regression and classification tasks. The experimental results validate that on the PASCAL VOC and COCO datasets, compared with the FSOD baselines of original contrastive learning, the proposed method improves the average accuracy of the novel and the base classes by 1.3%similar to 15.1% and 7% separately, both of which reach the SOTA level.

关键词： few-shot object detection contrastive learning overcoming catastrophic forgetting

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

Support-Query Mutual Promotion and Classification Correction Network for few-shot object detection

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 201-205页

作者： Xu, Jinbo Wang, Yong He, Xiaoyu Zou, Yiqun Cent South Univ Sch Automat Changsha 410083 Peoples R China

Recently, finetuning-based methods have shown great performance in few-shot object detection. These methods employ pure convolutional structures for feature extraction, and then finetune the last layers of the base detector on novel classes. However, most of them have the following two issues: 1) the feature extraction processes of support and query sets lack mutual promotion, and 2) the features extracted by pure convolutional structures have low discriminability for confused classes, which could lead to false positive results. To overcome these two issues, we propose a support-query mutual promotion and classification correction network (SMPCCNet). First, we build a support-query mutual promotion module. In this module, we perform class attention operations with query features to produce enhanced support features, and use the dense kernels generated by the enhanced support features to obtain support-relevant query features, which achieves the mutual promotion of support and query features. In addition, we design a classification correction branch with a hybrid attention module. The hybrid attention module uses spatial and channel attentions to generate features that focus on the positions and types of detected objects, respectively, which can better discriminate confused classes and correct false positive results. Extensive experiments demonstrate the superiority of SMPCCNet over state-of-the-art methods.

关键词： Class attention classification correction dense kernels few-shot object detection

来源：评论

学校读者我要写书评

暂无评论

SMDC-Net: Saliency-Guided Multihead Distribution Calibration Network for few-shot object detection on Remote Sensing Images

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2024年 21卷 1页

作者： Wu, Jiayi Qin, Chuan Feng, Guorui Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Univ Shanghai Sci & Technol Sch Opt Elect & Comp Engn Shanghai 200093 Peoples R China

object detection on remote sensing images (RSIs) is a critical component of RSI processing techniques. Nonetheless, as the complexity of the model structure increases, more training data is required to prevent a severe decline in object detection performance. This requirement highlights the potential of few-shot object detection techniques. At present, few researches have been investigated for few-shot object detection on RSIs. To address this situation, we propose the saliency-guided multihead distribution calibration network (SMDC-Net) by building upon the existing fine-tuning-based two-stage few-shot object detection approach. We employ an RSI salient object detection (SOD) branch that leverages the feature of RSIs to predict the saliency maps. These predicted saliency maps are used as an attention map to augment the feature of RSIs. Meanwhile, to guarantee the ability of the network to identify objects in both the base and novel categories accurately, we design a multihead detector that can recognize objects in base and novel categories separately while introducing a consistency loss to supervise the consistency of the multihead predicted labels. We evaluate the performance of two widely recognized RSI datasets (i.e., DIOR and NWPU VHR-10) in various experimental settings for comparison and ablation analysis. The results illustrate that SMDC-Net enhances the detection performance of novel categories by approximately 3% compared to the state-of-the-art MM-RCNN while preserving the performance of base categories.

关键词： Consistency supervision few-shot object detection remote sensing images (RSIs) salient object detection (SOD)

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Bi-path Combination YOLO for Real-time few-shot object detection

引用

PATTERN RECOGNITION LETTERS 2023年 165卷 91-97页

作者： Xia, Ruiyang Li, Guoquan Huang, Zhengwen Meng, Hongying Pang, Yu Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing 400065 Peoples R China BUL CQUPT Innovat Insitute Grp Artificial Intelligence & Syst Optimizat Chongqing 400065 Peoples R China Brunel Univ London Dept Elect & Elect Engn UB8-3PH London England Chongqing Univ Posts & Telecommun Key Lab Photoelect Informat Sensing & Transmiss Te Chongqing 400065 Peoples R China

few-shot object detection (FSOD) has more attention in recent years as the quantitative limitation of in-stances during the model training. Previous works based on meta learning and transfer learning focus on the detection precision but ignore the inferring speed, which is difficult to apply in amounts of applica-tions. In this letter, to keep a high inferring speed and a comparable detection precision, we propose a real-time detector entitled Bi-path Combination You Only Look Once (BC-YOLO) for FSOD. BC-YOLO can be categorized as a transfer learning based one-stage object detector with a two-phase training scheme. It is particularly composed of bi-path parallel detection branches which detect base and novel class objects respectively and commonly detect objects with a discriminator in the inferring stage. Moreover, to ele-vate the model generalization trained from few-shot objects, we further propose an Attentive DropBlock algorithm to make the detector focus on the entire details of objects instead of the local discriminative regions. Extensive experiments on PASCAL VOC 2007 and MS COCO 2014 datasets demonstrate that our method can achieve a better tradeoff between speed and precision than state-of-the-art methods.(c) 2022 Elsevier B.V. All rights reserved.

关键词： few-shot object detection Transfer learning Real-time Bi-path Combination You Only Look Once Attentive DropBlock

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：