检索结果-内蒙古大学图书馆

2024 International Conference on Machine Learning and Intelligent Computing, MLIC 2024

作者： Zhou, Peng Liu, Anzhan Zhongyuan University of Technology Zhengzhou450007 China

few-shot object detection models often lack the perceptual ability to detect the target objects and fine-tuning the model on base class images to quickly adapt to new tasks can lead to feature shift issues. We propose an Adaptive Meta-Feature Weighting (AMFW-YOLO) object detection model for solving these problems. This model introduces an attention mechanism based on spatial and channel-wise squeeze-and-excitation (scSE) blocks, which helps the model focus on the regions of interest in the target samples and suppresses interference from background regions. Additionally, to compensate for the feature shift caused during the fine-tuning stage, we design an Adaptive Meta-Feature Weighting module (AMFW), This module embeds positional information into spatial features, captures long-range dependencies along two directions, and adaptively compensates for the weights of deep global features, effectively improving the accuracy of the model. © 2024 P. Zhou & A. Liu.

关键词： Adaptive Meta-feature weighting Feature Reweighting few-shot Learning few-shot object detection

来源：评论

学校读者我要写书评

暂无评论

Text Semantic Fusion Relation Graph Reasoning for few-shot object detection on Remote Sensing Images

引用

REMOTE SENSING 2023年第5期15卷 1187页

作者： Zhang, Sanxing Song, Fei Liu, Xianyuan Hao, Xuying Liu, Yujia Lei, Tao Jiang, Ping Chinese Acad Sci Inst Opt & Elect Chengdu 610209 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 101408 Peoples R China Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

Most object detection methods based on remote sensing images are generally dependent on a large amount of high-quality labeled training data. However, due to the slow acquisition cycle of remote sensing images and the difficulty in labeling, many types of data samples are scarce. This makes few-shot object detection an urgent and necessary research problem. In this paper, we introduce a remote sensing few-shot object detection method based on text semantic fusion relation graph reasoning (TSF-RGR), which learns various types of relationships from common sense knowledge in an end-to-end manner, thereby empowering the detector to reason over all classes. Specifically, based on the region proposals provided by the basic detection network, we first build a corpus containing a large number of text language descriptions, such as object attributes and relations, which are used to encode the corresponding common sense embeddings for each region. Then, graph structures are constructed between regions to propagate and learn key spatial and semantic relationships. Finally, a joint relation reasoning module is proposed to actively enhance the reliability and robustness of few-shot object feature representation by focusing on the degree of influence of different relations. Our TSF-RGR is lightweight and easy to expand, and it can incorporate any form of common sense information. Sufficient experiments show that the text information is introduced to deliver excellent performance gains for the baseline model. Compared with other few-shot detectors, the proposed method achieves state-of-the-art performance for different shot settings and obtains highly competitive results on two benchmark datasets (NWPU VHR-10 and DIOR).

关键词： few-shot object detection relation reasoning remote sensing images gated graph neural network (GGNN)

来源：评论

学校读者我要写书评

暂无评论

Re-scoring using image-language similarity for few-shot object detection

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2024年 241卷

作者： Jung, Min Jae Han, Seung Dae Kim, Joohee Infiniq ALab Seoul 06232 South Korea

few-shot object detection, which focuses on detecting novel objects with few labels, is an emerging challenge in the community. Recent studies show that adapting a pre-trained model or modified loss function can improve performance. In this paper, we explore leveraging the power of Contrastive Language-Image Pre -training (CLIP) and hard negative classification loss in low data setting. Specifically, we propose Re -scoring using Image-language Similarity for few-shot object detection (RISF) which extends Faster R-CNN by introducing Calibration Module using CLIP (CM -CLIP) and Background Negative Re-scale Loss (BNRL). The former adapts CLIP, which performs zero-shot classification, to re -score the classification scores of a detector using image-class similarities, the latter is modified classification loss considering the punishment for fake backgrounds as well as confusing categories on a generalized few-shot object detection dataset. Extensive experiments on MS -COCO and PASCAL VOC show that the proposed RISF substantially outperforms the state -of -the -art approaches. Code is available at: https://***/INFINIQ-AI1/RISF

关键词： few-shot object detection few-shot Learning object detection Vision-language multi modal Classification loss

来源：评论

学校读者我要写书评

暂无评论

Prototype-CNN for few-shot object detection in Remote Sensing Images

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Cheng, Gong Yan, Bowei Shi, Peizhen Li, Ke Yao, Xiwen Guo, Lei Han, Junwei Northwestern Polytech Univ Res & Dev Inst Shenzhen 518057 Peoples R China Northwestern Polytech Univ Sch Automat Xian 710129 Peoples R China Zhengzhou Inst Surveying & Mapping Zhengzhou 450052 Peoples R China

Recently, due to the excellent representation ability of convolutional neural networks (CNNs), object detection in remote sensing images has undergone remarkable development. However, when trained with a small number of samples, the performance of the object detectors drops sharply. In this article, we focus on the following three main challenges of few-shot object detection in remote sensing images: 1) since the sample number of novel classes is far less than base classes, object detectors would fail to quickly adapt to the features of novel classes, which would result in overfitting;2) the scarcity of samples in novel classes leads to a sparse orientation space, while the objects in remote sensing images usually have arbitrary orientations;and 3) the distribution of object instances in remote sensing images is scattered and, therefore, it is hard to identify foreground objects from the complex background. To tackle these problems, we propose a simple yet effective method named prototype-CNN (P-CNN), which mainly consists of three parts: a prototype learning network (PLN) converting support images to class-aware prototypes, a prototype-guided region proposal network (P-G RPN) for better generation of region proposals, and a detector head extending the head of Faster region-based CNN (R-CNN) to further boost the performance. Comprehensive evaluations on the large-scale DIOR dataset demonstrate the effectiveness of our P-CNN. The source code is available at https://***/Ybowei/P-CNN.

关键词： Remote sensing object detection Proposals Prototypes Training Task analysis Feature extraction Convolutional neural network (CNN) few-shot object detection prototype-CNN (P-CNN) remote sensing images

来源：评论

学校读者我要写书评

暂无评论

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2024年 105卷

作者： Zhu, Songhao Wang, Yi Nanjing Univ Posts & Telecommun Coll Automat & Artificial Intelligence Nanjing Peoples R China

few-shot object detection method aims to learn novel classes through a small number of annotated novel class samples without having a catastrophic impact on previously learned knowledge, thereby expanding the trained model's ability to detect novel classes. For existing few-shot object detection methods, there is a prominent false positive issue for the novel class samples due to the similarity in appearance features and feature distribution between the novel classes and the base classes. That is, the following two issues need to be solved: (1) How to detect these false positive samples in large-scale dataset, and (2) How to utilize the correlations between these false positive samples and other samples to improve the accuracy of the detection model. To address the first issue, an adaptive fusion data augmentation strategy is utilized to enhance the diversity of novel class samples and further alleviate the issue of false positive novel class samples. To address the second issue, a similarity transfer strategy is here proposed to effectively utilize the correlations between different categories. Experimental results demonstrate that the proposed method performs well in various settings of PASCAL VOC and MSCOCO datasets, achieving 48.7 and 11.3 on PASCAL VOC and MSCOCO under few-shot settings (shot = 1) in terms of nAP50 respectively.

关键词： few-shot object detection Fine tuning Similarity transfer Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Improved region proposal network for enhanced few-shot object detection

引用

NEURAL NETWORKS 2024年 180卷 106699页

作者： Shangguan, Zeyu Rostami, Mohammad Univ Southern Calif Dept Comp Sci 3650 McClintock Ave Los Angeles CA 90089 USA

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and time-consuming endeavor, particularly when dealing with infrequent objects. few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches based on deep learning. FSOD methods demonstrate remarkable performance by achieving robust object detection using a significantly smaller amount of training data. A challenge for FSOD is that instances from novel classes that do not belong to the fixed set of training classes appear in the background and the base model may pick them up as potential objects. These objects behave similarly to label noise because they are classified as one of the training dataset classes, leading to FSOD performance degradation. We develop a semi-supervised algorithm to detect and then utilize these unlabeled novel objects as positive samples during the FSOD training stage to improve FSOD performance. Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects. We test our approach and COCO and PASCAL VOC baselines that are commonly used in FSOD literature. Our experimental results indicate that our method is effective and outperforms the existing state-of-the-art (SOTA) FSOD methods.

关键词： few-shot object detection Semi-supervised learning Region proposal network

来源：评论

学校读者我要写书评

暂无评论

Feature reconstruction and metric based network for few-shot object detection

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2023年 227卷

作者： Li, Yuewen Feng, Wenquan Lyu, Shuchang Zhao, Qi Dept Elect & Informat Engn Beijing 100191 Peoples R China

In the object detection task, deep learning-based methods always need a large amount of annotated training data. However, annotating a large number of images is labor-intensive. In order to reduce the dependency of expensive annotations, we propose a novel end-to-end feature reconstruction and metric based network for few-shot object detection (FM-FSOD). FM-FSOD integrates metric learning and meta-learning to tackle the few-shot object detection task. FM-FSOD is a class-agnostic detection model that can accurately recognize novel categories without fine-tuning on novel categories. Specifically, to quickly learn the characteristics of novel categories, we propose a meta-representation module (MR module) to learn from intra-class mean prototypes and acquire the ability to reconstruct high-level features with the meta-learning method. To further conduct the similarity of features between support prototypes and query ROI features, we propose Pearson metric module (PR module), which serves as a classifier. Compared with the previous standard cosine distance module, the PR module enables the model to acquire robust ability for large bias features. We have conducted extensive experiments on benchmark datasets FSOD, MS COCO, and PASCAL VOC to demonstrate the feasibility and efficiency of our model. Comparing with the previous methods, FM-FSOD obtains comparable results.

关键词： few-shot object detection Meta-learning Metric learning Feature representation Pearson distance

来源：评论

学校读者我要写书评

暂无评论

Context Information Refinement for few-shot object detection in Remote Sensing Images

引用

REMOTE SENSING 2022年第14期14卷 3255页

作者： Wang, Yan Xu, Chaofei Liu, Cuiwei Li, Zhaokui Shenyang Aerosp Univ Sch Comp Sci Shenyang 110136 Peoples R China

Recently, few-shot object detection based on fine-tuning has attracted much attention in the field of computer vision. However, due to the scarcity of samples in novel categories, obtaining positive anchors for novel categories is difficult, which implicitly introduces the foreground-background imbalance problem. It is difficult to identify foreground objects from complex backgrounds due to various object sizes and cluttered backgrounds. In this article, we propose a novel context information refinement few-shot detector (CIR-FSD) for remote sensing images. In particular, we design a context information refinement (CIR) module to extract discriminant context features. This module uses dilated convolutions and dense connections to capture rich context information from different receptive fields and then uses a binary map as the supervision label to refine the context information. In addition, we improve the region proposal network (RPN). Concretely, the RPN is fine-tuned on novel categories, and the constraint of non-maximum suppression (NMS) is relaxed, which can obtain more positive anchors for novel categories. Experiments on two remote sensing public datasets show the effectiveness of our detector.

关键词： convolutional neural network (CNN) few-shot object detection remote sensing images context information

来源：评论

学校读者我要写书评

暂无评论

MSFFAL: few-shot object detection via Multi-Scale Feature Fusion and Attentive Learning

引用

SENSORS 2023年第7期23卷 3609-3609页

作者： Zhang, Tianzhao Sun, Ruoxi Wan, Yong Zhang, Fuping Wei, Jianming Chinese Acad Sci Shanghai Adv Res Inst Shanghai 201210 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Chinese Acad Sci Inst Rock & Soil Mech State Key Lab Geomech & Geotech Engn Wuhan 430071 Peoples R China

few-shot object detection (FSOD) is proposed to solve the application problem of traditional detectors in scenarios lacking training samples. The meta-learning methods have attracted the researchers' attention for their excellent generalization performance. They usually select the same class of support features according to the query labels to weight the query features. However, the model cannot possess the ability of active identification only by using the same category support features, and feature selection causes difficulties in the testing process without labels. The single-scale feature of the model also leads to poor performance in small object detection. In addition, the hard samples in the support branch impact the backbone's representation of the support features, thus impacting the feature weighting process. To overcome these problems, we propose a multi-scale feature fusion and attentive learning (MSFFAL) framework for few-shot object detection. We first design the backbone with multi-scale feature fusion and channel attention mechanism to improve the model's detection accuracy on small objects and the representation of hard support samples. Based on this, we propose an attention loss to replace the feature weighting module. The loss allows the model to consistently represent the objects of the same category in the two branches and realizes the active recognition of the model. The model no longer depends on query labels to select features when testing, optimizing the model testing process. The experiments show that MSFFAL outperforms the state-of-the-art (SOTA) by 0.7-7.8% on the Pascal VOC and exhibits 1.61 times the result of the baseline model in MS COCO's small objects detection.

关键词： few-shot object detection few-shot learning attention mechanism multi-scale feature fusion

来源：评论

学校读者我要写书评

暂无评论

Scale Information Enhancement for few-shot object detection on Remote Sensing Images

引用

REMOTE SENSING 2023年第22期15卷 5372-5372页

作者： Yang, Zhenyu Zhang, Yongxin Zheng, Jv Yu, Zhibin Zheng, Bing Piciarelli, Claudio Melo-Pinto, Pedro Ocean Univ China Fac Informat Sci & Engn Qingdao 266100 Peoples R China Ocean Univ China Sanya Oceanog Inst Key Lab Ocean Observat & Informat Hainan Prov Sanya 572024 Peoples R China

Recently, deep learning-based object detection techniques have arisen alongside time-consuming training and data collection challenges. Although few-shot learning techniques can boost models with few samples to lighten the training load, these approaches still need to be improved when applied to remote-sensing images. objects in remote-sensing images are often small with an uncertain scale. An insufficient amount of samples would further aggravate this issue, leading to poor detection performance. This paper proposes a Gaussian-scale enhancement (GSE) strategy and a multi-branch patch-embedding attention aggregation (MPEAA) module for cross-scale few-shot object detection to address this issue. Our model can enrich the scale information of an object and learn better multi-scale features to improve the performance of few-shot object detectors on remote sensing images.

关键词： few-shot object detection meta learning remote sensing images scale information

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：