检索结果-内蒙古大学图书馆

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Tong, Jiaxing Chen, Tao Wang, Qiong Yao, Yazhou Nanjing Univ Sci & Technol Nanjing 210094 Peoples R China

ISBN: (纸本)9783031189067;9783031189074

few-shot object detection (FSOD) aims to make the detector adapt to unseen classes with only a few training samples. Typical FSOD methods use Faster R-CNN as the basic detection framework, which utilizes convolutional neural networks to extract image features. However, pooling operations adopted in convolutional neural networks aiming to capture as much image information as possible will inevitably lead to the loss of image information. Therefore, we introduce Hybrid Dilated Convolution (HDC) in the backbone network to ensure a larger receptive field and minimize the loss of image information. Besides, in the k-shot (k = 2) setting, we notice that previous methods use an average aggregation operation to fuse the support features of each category. This operation treats every support sample equally, obviously under-utilizing the limited samples. In order to further take advantage of the given support data, we propose a Support Features Dynamic Fusion (SFDF) module. Our proposed SFDF module takes the correlation between each support feature and the query feature as the weight to fuse the support features adaptively for more robust support clues. Experiments demonstrate that our proposed method achieves state-of-the-art FSOD performance on public Pascal VOC and MS-COCO datasets.

关键词： few-shot object detection Hybrid dilated convolution Support features dynamic fusion

来源：评论

学校读者我要写书评

暂无评论

few-shot object detection with Model Calibration 17th

Few-Shot Object Detection with Model Calibration

引用

17th European Conference on Computer Vision (ECCV)

作者： Fan, Qi Tang, Chi-Keung Tai, Yu-Wing Hong Kong Univ Sci & Technol Clear Water Bay Hong Kong Peoples R China Kuaishou Technol Beijing Peoples R China

ISBN: (纸本)9783031197994;9783031198007

few-shot object detection (FSOD) targets at transferring knowledge from known to unknown classes to detect objects of novel classes. However, previous works ignore the model bias problem inherent in the transfer learning paradigm. Such model bias causes overfitting toward the training classes and destructs the well-learned transferable knowledge. In this paper, we pinpoint and comprehensively investigate the model bias problem in FSOD models and propose a simple yet effective method to address the model bias problem with the facilitation of model calibrations in three levels: 1) Backbone calibration to preserve the well-learned prior knowledge and relieve the model bias toward base classes, 2) RPN calibration to rescue unlabeled objects of novel classes and, 3) Detector calibration to prevent the model bias toward a few training samples for novel classes. Specifically, we leverage the overlooked classification dataset to facilitate our model calibration procedure, which has only been used for pre-training in other related works. We validate the effectiveness of our model calibration method on the popular Pascal VOC and MS COCO datasets, where our method achieves very promising performance. Codes are released at https://***/fanq15/fewX.

关键词： few-shot object detection Model bias Model calibration Uncertainty-aware RPN Detector calibration

来源：评论

学校读者我要写书评

暂无评论

few-shot object detection with Refined Contrastive Learning 35

Few-shot Object Detection with Refined Contrastive Learning

引用

35th IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Shangguan, Zeyu Huai, Lian Liu, Tong Jiang, Xingqun BOE Technol Grp Co Ltd AIoT CTO Beijing Peoples R China

ISBN: (纸本)9798350342734

Due to the scarcity of sampling data in reality, few-shot object detection (FSOD) has drawn more and more attention because of its ability to quickly train new detection concepts with less data. However, there are still failure identifications due to the difficulty in distinguishing confusable classes. We also notice that the high standard deviation of average precision reveals the inconsistent detection performance. To this end, we propose a novel FSOD method with Refined Contrastive Learning (FSRC). A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes. Afterwards, Refined Contrastive Learning (RCL) is pointedly performed on this group of classes in order to increase the inter-class distances among them. In the meantime, the detection results distribute more uniformly which further improve the performance. Experimental results based on PASCAL VOC and COCO datasets demonstrate our proposed method outperforms the current state-of-the-art research.

关键词： few-shot object detection transfer learning contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised few-shot object detection via Adaptive Pseudo Labeling

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第4期34卷 2151-2165页

作者： Tang, Yingbo Cao, Zhiqiang Yang, Yuequan Liu, Jierui Yu, Junzhi Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Yangzhou Univ Coll Informat Engn Yangzhou 225127 Peoples R China Yangzhou Univ Coll Artificial Intelligence Yangzhou 225127 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot BIC ESAT Beijing 100871 Peoples R China

few-shot object detection (FSOD) aims to detect novel objects with limited annotated examples. Mainstream methods suffer from the data scarcity of novel classes with insufficient intra-class variations, which makes the trained model biased to base classes. Actually, there are massive unlabeled novel instances in the base dataset and their adequate utilization will enhance the discriminability of model to novel classes. This paper proposes a semi-supervised few-shot object detection method, which utilizes a teacher model and a pre-trained few-shot object detector to guide the learning of a student model through adaptive pseudo labeling. In particular, a class-adaptive threshold filtering (CATF) strategy is designed to deal with the class-imbalance problem of pseudo labels. And for each novel class, the threshold to select valuable pseudo labels is determined by quantile statistics of the confidence score distribution of pseudo labels. Furthermore, the pre-trained detector and the teacher model are associated with the preliminary CATF and in-depth CATF, respectively, and then the pseudo labels from the two-stream CATF are fused to provide supervisions. In this way, the knowledge of these two models is exploited, which improves the quality of pseudo labels. Under these supervisions, the student model is trained and the teacher model is correspondingly updated through parameters sharing, thus forming a positive feedback to improve the performance of both models. Besides, an attention module is integrated to the teacher and student models to enhance the feature representation of novel instances. The validations on PASCAL VOC and MS COCO show the effectiveness of the proposed method.

关键词： Adaptation models object detection Data models Training Detectors Labeling Feature extraction few-shot object detection adaptive pseudo labeling semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Boosting few-shot object detection with Discriminative Representation and Class Margin

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第3期20卷 1-19页

作者： Shi, Yanyan Yang, Shaowu Yang, Wenjing Shi, Dianxi Li, Xuehui Natl Univ Def Technol Coll Comp Changsha Hunan Peoples R China Natl Innovat Inst Def Technol Changsha Peoples R China

Classifying and accurately locating a visual category with few annotated training samples in computer vision has motivated the few-shot object detection technique, which exploits transfering the source-domain detection model to the target domain. Under this paradigm, however, such transferred source-domain detection model usually encounters difficulty in the classification of the target domain because of the low data diversity of novel training samples. To combat this, we present a simple yet effective few-shot detector, Transferable RCNN. To transfer general knowledge learned from data-abundant base classes to data-scarce novel classes, we propose aweight transfer strategy to promote model transferability and an attention-based feature enhancement mechanism to learn more robust object proposal feature representations. Further, we ensure strong discrimination by optimizing the contrastive objectives of feature maps via a supervised spatial contrastive loss. Meanwhile, we introduce an angle-guided additive margin classifier to augment instance-level inter-class difference and intra-class compactness, which is beneficial for improving the discriminative power of the few-shot classification head under a few supervisions. Our proposed framework outperforms the current works in various settings of PASCAL VOC and MSCOCO datasets;this demonstrates the effectiveness and generalization ability.

关键词： Deep learning few-shot object detection transfer learning

来源：评论

学校读者我要写书评

暂无评论

ECEA: Extensible Co-Existing Attention for few-shot object detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 5564-5576页

作者： Xin, Zhimeng Wu, Tianxu Chen, Shiming Zou, Yixiong Shao, Ling You, Xinge Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect Informat & Commun Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China Univ Chinese Acad Sci UCAS UCAS Terminus AI Lab Beijing 100101 Peoples R China

few-shot object detection (FSOD) identifies objects from extremely few annotated samples. Most existing FSOD methods, recently, apply the two-stage learning paradigm, which transfers the knowledge learned from abundant base classes to assist the few-shot detectors by learning the global features. However, such existing FSOD approaches seldom consider the localization of objects from local to global. Limited by the scarce training data in FSOD, the training samples of novel classes typically capture part of objects, resulting in such FSOD methods being unable to detect the completely unseen object during testing. To tackle this problem, we propose an Extensible Co-Existing Attention (ECEA) module to enable the model to infer the global object according to the local parts. Specifically, we first devise an extensible attention mechanism that starts with a local region and extends attention to co-existing regions that are similar and adjacent to the given local region. We then implement the extensible attention mechanism in different feature scales to progressively discover the full object in various receptive fields. In the training process, the model learns the extensible ability on the base stage with abundant samples and transfers it to the novel stage of continuous extensible learning, which can assist the few-shot model to quickly adapt in extending local regions to co-existing regions. Extensive experiments on the PASCAL VOC and COCO datasets show that our ECEA module can assist the few-shot detector to completely predict the object despite some regions failing to appear in the training samples and achieve the new state-of-the-art compared with existing FSOD methods. Code is released at https://***/zhimengXin/ECEA.

关键词： Training Detectors object detection Feature extraction Task analysis Semantics Adaptation models few-shot object detection extensible attention co-existing regions

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

SD-FSOD: Self-Distillation Paradigm via Distribution Calibration for few-shot object detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第7期34卷 5963-5976页

作者： Chen, Han Wang, Qi Xie, Kailin Lei, Liang Lin, Matthieu Gaetan Lv, Tian Liu, Yongjin Luo, Jiebo Guangdong Univ Technol Guangzhou 510006 Peoples R China Guizhou Univ Coll Comp Sci & Technol State Key Lab Publ Big Data Guiyang 550025 Guizhou Peoples R China Tsinghua Univ Coll Comp Sci & Technol Beijing 100084 Peoples R China Univ Rochester Dept Comp Sci Rochester NY 14627 USA

few-shot object detection (FSOD) aims to detect novel targets with only a few instances of the associated samples. Although combinations of distillation techniques and meta-learning paradigms have been acknowledged as the primary strategies for FSOD tasks, the existing distillation methods exhibit inherent biases and sensitivity to novel class variability. A critical hurdle for FSOD distillation is the difficulty in ensuring appropriate knowledge learned from the teacher model during the fine-tuning stage. Furthermore, coarse distillation procedures risk misalignment between the learned and actual distributions. This misalignment could potentially negate the benefits of positive cases and impede the detector's evolution. To address these deficiencies, we propose a novel self-distillation paradigm exclusively for the fine-tuning stage (SD-FSOD). Our methods integrate a Distribution Prototype Extractor (DPE) and Self-Distillation Memory (SDM), promoting feature distribution consistency during distillation. In detail, the DPE module reliably initializes the weights of the detector, ensuring a robust class distribution for the distillation process. Meanwhile, the SDM module utilizes decoupling techniques to divide the distillation tasks into two sub-task branches, allowing the student model to independently learn and share precise features through isolated distillation processes. The synergistic integration of feature calibration techniques and the continuous self-distillation paradigm distinctly enhances the fine-tuning process, which shows the superiority of the FSOD self-distillation methodologies. The extensive experiments on the PASCAL VOC and MS COCO datasets demonstrate that our proposed approach produces significant improvements and achieves state-of-the-art (SOTA) performance.

关键词： Prototypes Task analysis object detection Feature extraction Calibration Predictive models Detectors few-shot object detection self-distillation distribution prototype decoupled sub-tasks

来源：评论

学校读者我要写书评

暂无评论

Extreme R-CNN: few-shot object detection via Sample Synthesis and Knowledge Distillation

引用

SENSORS 2024年第23期24卷 7833页

作者： Zhang, Shenyong Wang, Wenmin Wang, Zhibing Li, Honglei Li, Ruochen Zhang, Shixiong Macau Univ Sci & Technol Sch Comp Sci & Engn Macau 999078 Peoples R China Beijing Inst Technol Sch Comp Technol Zhuhai 519088 Peoples R China Chongqing Polytech Univ Elect Technol Artificial Intelligence & Big Data Coll Chongqing 401331 Peoples R China Guangdong BOHUA UHD Video Innovat Ctr Co Ltd Shenzhen 518172 Peoples R China

Traditional object detectors require extensive instance-level annotations for training. Conversely, few-shot object detectors, which are generally fine-tuned using limited data from unknown classes, tend to show biases toward base categories and are susceptible to variations within these unknown samples. To mitigate these challenges, we introduce a Two-Stage Fine-Tuning Approach (TFA) named Extreme R-CNN, designed to operate effectively with extremely limited original samples through the integration of sample synthesis and knowledge distillation. Our approach involves synthesizing new training examples via instance clipping and employing various data-augmentation techniques. We enhance the Faster R-CNN architecture by decoupling the regression and classification components of the Region of Interest (RoI), allowing synthetic samples to train the classification head independently of the object-localization process. Comprehensive evaluations on the Microsoft COCO and PASCAL VOC datasets demonstrate significant improvements over baseline methods. Specifically, on the PASCAL VOC dataset, the average precision for novel categories is enhanced by up to 15 percent, while on the more complex Microsoft COCO benchmark it is enhanced by up to 6.1 percent. Remarkably, in the 1-shot scenario, the AP50 of our model exceeds that of the baseline model in the 10-shot setting within the PASCAL VOC dataset, confirming the efficacy of our proposed method.

关键词： two-stage fine-tuning approach few-shot object detection synthesizing sample knowledge distillation triplet loss

来源：评论

学校读者我要写书评

暂无评论

Understanding Negative Proposals in Generic few-shot object detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第7期34卷 5818-5829页

作者： Yan, Bowei Lang, Chunbo Cheng, Gong Han, Junwei Northwestern Polytech Univ Sch Automat Xian 710129 Peoples R China

Recently, few-shot object detection (FSOD) has received considerable research attention as a strategy for reducing reliance on extensively labeled bounding boxes. However, current approaches encounter significant challenges due to the intrinsic issue of incomplete annotation while building the instance-level training benchmark. In such cases, the instances with missing annotations are regarded as background, resulting in erroneous training gradients back-propagated through the detector, thereby compromising the detection performance. To mitigate this challenge, we introduce a simple and highly efficient method that can be plugged into both meta-learning-based and transfer-learning-based methods. Our method incorporates two innovative components: Confusing Proposals Separation (CPS) and Affinity-Driven Gradient Relaxation (ADGR). Specifically, CPS effectively isolates confusing negatives while ensuring the contribution of hard negatives during model fine-tuning;ADGR then adjusts their gradients based on the affinity to different category prototypes. As a result, false-negative samples are assigned lower weights than other negatives, alleviating their harmful impacts on the few-shot detector without the requirement of additional learnable parameters. Extensive experiments conducted on the PASCAL VOC and MS-COCO datasets consistently demonstrate that our method significantly outperforms both the baseline and recent FSOD methods. Furthermore, its versatility and efficiency suggest the potential to become a stronger new baseline in the field of FSOD. Code is available at https://***/Ybowei/UNP.

关键词： Deep learning few-shot object detection few-shot learning incomplete annotation sampling algorithm

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：