检索结果-内蒙古大学图书馆

Intervening on few-shot object detection based on the front-door criterion

NEURAL NETWORKS 2025年 185卷 107251页

作者： Zhang, Yanan Li, Jiangmeng Ji, Qirui Li, Kai Liu, Lixiang Zheng, Changwen Qiang, Wenwen Univ Chinese Acad Sci Beijing Peoples R China Chinese Acad Sci Inst Software Natl Key Lab Space Integrated Informat Syst Beijing Peoples R China

Most few-shot object detection methods aim to utilize the learned generalizable knowledge from base categories to identify instances of novel categories. The fundamental assumption of these approaches is that the model can acquire sufficient transferable knowledge through the learning of base categories. However, our motivating experiments reveal a phenomenon that the model is overfitted to the data of base categories. To discuss the impact of this phenomenon on detection from a causal perspective, we develop a Structural Causal Model involving two key variables, causal generative factors and spurious generative factors. Both variables are derived from the base categories. Generative factors are latent variables or features that are used to control image generation. Causal generative factors are general generative factors that directly influence the generation process, while spurious generative factors are specific to certain categories, specifically the base categories in the problem we are analyzing. We recognize that the essence of the few-shot object detection methods lies in modeling the statistic dependence between novel object instances and their corresponding categories determined by the causal generative factors, while the set of spurious generative factors serves as a confounder in the modeling process. To mitigate the misleading impact of the spurious generative factors, we propose the Front-door Regulator guided by the front-door criterion. Front-door Regulator consists of two plug-and-play regularization terms, namely Semantic Grouping and Semantic Decoupling. We substantiate the effectiveness of our proposed method through experiments conducted on multiple benchmark datasets.

关键词： few-shot object detection Overfitting Front-door adjustment Causal inference

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Progressive Network for few-shot object detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 264卷

作者： Wang, Bingxin Yu, Dehong Xi An Jiao Tong Univ 28 Xianning West Rd Xian 710049 Shaanxi Peoples R China

few-shot object detection (FSOD) is a significant application of few-shot learning in object detection tasks. Its primary objective is to enable the model to quickly acquire the ability to detect novel categories through a limited number of annotated samples. However, such a small number of training samples is insufficient for the model to be fully trained, which leads to difficulties in completely decoupling the regression and classification tasks, and confusion among categories. To address this issue, this paper proposes to remap features into location and class spaces. By imposing task orthogonality and class orthogonality constraints on the finetuning process, task decoupling and class decoupling are achieved. Furthermore, we design and implement a progressive fine-tuning strategy that iteratively optimizes in a lagged and progressive manner through the combination of training samples and historical features, mitigating the risks of catastrophic forgetting and overfitting. Experimental results demonstrate that our method effectively improves the model's performance in FSOD tasks, achieving state-of-the-art metrics on the PASCAL VOC and MS COCO benchmarks.

关键词： few-shot object detection Task orthogonality Class orthogonality Progressive fine-tuning strategy

来源：评论

学校读者我要写书评

暂无评论

Dynamic relevance learning for few-shot object detection

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第4期19卷 1-10页

作者： Liu, Weijie Cai, Xiaojie Wang, Chong Li, Haohe Yu, Shenghao Ningbo Univ Fac Elect Engn & Comp Sci Ningbo 315000 Peoples R China

Expensive bounding-box annotations have limited the development of object detection task. Thus, it is necessary to focus on more challenging task of few-shot object detection. It requires the detector to recognize objects of novel classes with only a few training samples. Nowadays, many existing popular methods adopting training way similar to meta-learning have achieved promising performance, such as Meta R-CNN series. However, support data is only used as the class attention to guide the detecting of query images each time. Their relevance to each other remains unexploited. Moreover, a lot of recent works treat the support data and query images as independent branch without considering the relationship between them. To address this issue, we propose a dynamic relevance learning model, which utilizes the relationship between all support images and Region of Interest (RoI) on the query images to construct a dynamic graph convolutional network (GCN). By adjusting the prediction distribution of the base detector using the output of this GCN, the proposed model serves as a hard auxiliary classification task, which guides the detector to improve the class representation implicitly. Comprehensive experiments conducted on Pascal VOC and MS-COCO datasets achieve competitive results, which shows its effectiveness of learning more generalized features. Our code is available at https://***/liuweijie19980216/DRL-for-FSOD.

关键词： few-shot object detection Meta R-CNN Graph convolutional networks Dynamic relevance learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Fine-Grained few-shot object detection on Remote Sensing Images with Decoupled Self-Distillation and Progressive Prototype Calibration

引用

REMOTE SENSING 2025年第3期17卷 495-495页

作者： Guo, Hao Liu, Yanxing Pan, Zongxu Hu, Yuxin Chinese Acad Sci Aerosp Informat Res Inst Beijing 100094 Peoples R China Chinese Acad Sci Key Lab Technol Geospatial Informat Proc & Applica Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Key Lab Target Cognit & Applicat Technol Beijing 100190 Peoples R China

In data-scarcity scenarios, few-shot object detection (FSOD) methods exhibit a notable advantage in alleviating the over-fitting problem. Currently, research on FSOD in the field of remote sensing is advancing rapidly and FSOD methods based on the fine-tuning paradigm have initially displayed their excellent performance. However, existing fine-tuning methods often encounter classification confusion issues. This is potentially because of the shortage of explicit modeling for transferable common knowledge and the biased class distribution, especially for fine-grained targets with higher inter-class similarity and intra-class variance. In view of this, we first propose a decoupled self-distillation (DSD) method to construct class prototypes in two decoupled feature spaces and measure inter-class correlations as soft labels or aggregation weights. To ensure a robust set of class prototypes during the self-distillation process, we devise a feature filtering module (FFM) to preselect high-quality class representative features. Furthermore, we introduce a progressive prototype calibration module (PPCM) with two steps, compensating the base prototypes with the prior base distribution and then calibrating the novel prototypes with adjacent calibrated base prototypes. Experiments on MAR20 and customized SHIP20 datasets have demonstrated the superior performance of our method compared to other existing advanced FSOD methods, simultaneously confirming the effectiveness of all proposed components.

关键词： remote sensing images few-shot object detection fine-grained object detection self-distillation prototype calibration

来源：评论

学校读者我要写书评

暂无评论

Enhanced few-shot object detection for remote sensing images based on target characteristics

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 148卷

作者： Wang, Jian Zhao, Zeya Shao, Jiang Zou, Xiaochun Zhao, Xinbo Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Beijing Inst Tracking & Commun Technol Beijing 100094 Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China

few-shot object detection (FSOD) in remote sensing images (RSIs) is a challenging and hot issue due to the characteristics of targets in remote sensing images such as varying sizes, complex backgrounds, target occlusions, and unbalanced target categories. Two-stage fine-tuning approach (TFA) has been shown to be the most competitive approach for few-shot learning. However, previous methods of fine-tuning remote sensing images using single-feature improvements had a limited effect on the result. In this paper, we propose a novel few-shot object detection method that coordinates multiple methods to gradually improve detection accuracy by focusing on the characteristics of remote sensing targets. More specifically, our model contains three main components: a novel context-aware weighted feature fusion module (CA-WFFM) that enhances the discrimination between background and foreground structures in complex scenarios, an edge detection block (EDB), which combines handcrafted features, that enhances the stability of the network when the target is occluded or the sample is limited, and a selective random neighborhood oversampling (SRNO) strategy, that balances the base and novel category samples. These coordinated improvements were evaluated using the Drones In Optics Recognition (DIOR) and NWPU-VHR-10.v2 (VHR-10.v2) datasets with multiple training sample splits. Experimental results indicate that our method surpasses existing methods in novel class detection and also provides a new research approach for few-shot object detection. This involves designing algorithms based on target characteristics to enhance the overall detection capability of few-shot object detection models.

关键词： few-shot object detection Remote sensing images object detection Target characteristics

来源：评论

学校读者我要写书评

暂无评论

Learning General and Specific Embedding with Transformer for few-shot object detection

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第2期133卷 968-984页

作者： Zhang, Xu Chen, Zhe Zhang, Jing Liu, Tongliang Tao, Dacheng Univ Sydney Fac Engn Sch Comp Sci Darlington NSW 2008 Australia Trobe Univ Cisco La Trobe Ctr AI & IoT Sch Comp Engn & Math Sci Bendigo Vic 3552 Australia

few-shot object detection (FSOD) studies how to detect novel objects with few annotated examples effectively. Recently, it has been demonstrated that decent feature embeddings, including the general feature embeddings that are more invariant to visual changes and the specific feature embeddings that are more discriminative for different object classes, are both important for FSOD. However, current methods lack appropriate mechanisms to sensibly cooperate both types of feature embeddings based on their importance to detecting objects of novel classes, which may result in sub-optimal performance. In this paper, to achieve more effective FSOD, we attempt to explicitly encode both general and specific feature embeddings using learnable tensors and apply a Transformer to help better incorporate them in FSOD according to their relations to the input object features. We thus propose a Transformer-based general and specific embedding learning (T-GSEL) method for FSOD. In T-GSEL, learnable tensors are employed in a three-stage pipeline, encoding feature embeddings in general level, intermediate level, and specific level, respectively. In each stage, we apply a Transformer to first model the relations of the corresponding embedding to input object features and then apply the estimated relations to refine the input features. Meanwhile, we further introduce cross-stage connections between embeddings of different stages to make them complement and cooperate with each other, delivering general, intermediate, and specific feature embeddings stage by stage and utilizing them together for feature refinement in FSOD. In practice, a T-GSEL module is easy to inject. Extensive empirical results further show that our proposed T-GSEL method achieves compelling FSOD performance on both PASCAL VOC and MS COCO datasets compared with other state-of-the-art approaches.

关键词： few-shot object detection Transformer Feature embedding refinement

来源：评论

学校读者我要写书评

暂无评论

Multiscale Dynamic Attention and Hierarchical Spatial Aggregation for few-shot object detection

引用

APPLIED SCIENCES-BASEL 2025年第3期15卷 1381-1381页

作者： An, Yining Song, Chunlin Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China

few-shot object detection (FSOD) remains a critical challenge in computer vision, where the limited training data significantly hinder model performance. Existing methods suffer from poor robustness and accuracy, primarily due to scale sparsity and inadequate feature extraction. In this paper, we propose MDA-HAPP, a novel framework built on a transfer learning architecture and a two-stage object detection approach, specifically designed to address these issues. The key innovations of MDA-HAPP include 1. MultiScale-DynaAttention, a novel attention module that enhances feature extraction by integrating multi scale convolutions into channel attention and applying a dynamic pooling ratio to spatial attention, with residual connections to improve robustness;2. hierarchical adaptive-pyramid pooling, designed based on a spatial pyramid pooling (SPP) structure, extracts multiscale features from intermediate layers and dynamically adjusts pooling strategies. These features are then fed into a dual-branch detection head for comprehensive *** experimental results on the PASCAL VOC and COCO datasets show that MDA-HAPP achieves significant improvements across different K-shot settings. Specifically, the model demonstrates an up to 9.8% gain in AP75 on PASCAL VOC for K-shot values of 10 and an up to 3.7% improvement on COCO for K-shot values of 30. These results confirm its superior performance in FSOD and highlight its potential for real-world applications.

关键词： transfer learning few-shot object detection multiscale dynamic attention hierarchical adaptive-pyramid pooling

来源：评论

学校读者我要写书评

暂无评论

A few-shot object detection method for garbage via variational autoencoders and feature aggregation

引用

WASTE MANAGEMENT 2025年 200卷 114754页

作者： Xue, Shuya Song, Dian Chen, Wei Zhao, Lei Zhou, Qian Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Soochow Univ Sch Polit Sci & Publ Adm Suzhou Peoples R China

Outdoor waste detection plays a pivotal role in environmental monitoring and waste management systems. Traditional garbage detectors rely heavily on a large amount of labelled data for training. However, these approaches are resource-intensive and ill-suited for waste categories that evolve quickly or are uncommon. To address the limitation, we propose a novel few-shot object detection (FSOD) method, named few-shot Garbage detection (FSGD), which is tailored to identify garbage with limited labelled data. In the context of garbage detection, the changes in waste shapes caused by human behaviours can result in situations where the support images fail to fully represent category information. To tackle the issue, we utilize variational autoencoders (VAEs) to infer class distributions and sample robust variational features, ensuring an accurate representation of the garbage categories. Moreover, we propose an advanced aggregation strategy to establish correlations between support and query features. This strategy addresses the common problem in FSOD where the Region Proposal Network (RPN) is insensitive to novel categories. Additionally, we separate the weight of backbone network shared by support and query branches, which improves performance in a simple yet efficient way. Extensive experiments demonstrate that our method outperforms existing state-of-the-art FSOD methods in all evaluated scenarios on garbage detection datasets. Furthermore, we evaluate the generalization ability of the proposed FSGD approach on the publicly available Pascal VOC dataset, and the results indicate that FSGD also performs better than compared methods on this dataset.

关键词： Garbage detection few-shot object detection Waste localization Waste recognition Variational Autoencoder Feature Aggregation

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

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：