Few-Shot Fine-Grained Ship Classification With a Foreground-Aware Feature Map Reconstruction Network

Li, Yangfan; Bian, Chunjiang

doi:10.1109/tgrs.2022.3172223

Cited by 17 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let the function described by the classifier be 𝑓(𝑥). The top-1 accuracy can be represented by Equation (7).…”

Section: 𝑎𝑐𝑐𝑢𝑟𝑎𝑐𝑦 =mentioning

confidence: 99%

“…Although the current visible-image-based maritime vessel classification algorithms have achieved good results in remote sensing images [4,5,6,7], it is difficult to maintain long-term stable acquisition of satellite remote sensing images in practical applications, which cannot guarantee continuous real-time observation and processing of maritime vessels. In contrast, by placing video surveillance equipment in ports or other seaward areas, the natural images of maritime targets can be acquired continuously and in real-time, which is more in line with daily security needs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Vessel classification algorithm based on the convolutional attention module for natural maritime images

Zhao¹,

Zheng²,

Zhang³

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

In recent years, to ensure the stable development of the marine economy, the analysis and processing of maritime vessel targets combined with natural light images have played a significant role. However, in scenes such as ports, there are sometimes background noises similar to vessel features, so the classifier based on the convolutional neural network cannot achieve good classification results. To pay more attention to effective information when classifying natural maritime images, we propose an efficient channel attention module (ECAM) and a re-parameterized spatial attention module (RSAM) through one-dimensional convolution and re-parameterization method. This paper combines ECAM and RSAM to present an efficient re-parameterized convolutional block attention module (ER-CBAM) to classify natural maritime images. Besides, in response to the current lack of large-scale natural marine image datasets, we established a natural maritime vessel image (NMVI) dataset. Experiments on NMVI show that by combining the proposed attention module, ResNet50 can achieve a top-1 accuracy score of 85.32% with almost no extra computational consumption and a 3.02% improvement compared to the previous 82.30%, which suggests that the proposed method is suitable for maritime scenarios.

show abstract

“…Let the function described by the classifier be 𝑓(𝑥). The top-1 accuracy can be represented by Equation (7).…”

Section: 𝑎𝑐𝑐𝑢𝑟𝑎𝑐𝑦 =mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Vessel classification algorithm based on the convolutional attention module for natural maritime images

Zhao¹,

Zheng²,

Zhang³

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

show abstract

“…Feature reconstruction is a classical approach for object tracking and feature alignment [30][31][32][33][34][39][40][41][42][43][44], and has been recently applied for few-shot image classification. Among these models, FRN [30] uses closed-form-solution to perform feature reconstruction directly, which is not only fast but also has excellent precision.…”

Section: Feature Reconstructionmentioning

confidence: 99%

“…MARPN proposes fewer but more accurate RoIs, which greatly reduces the burden on the head. Besides, MARPN introduces supervised learning to guide the generation of spatial attention, which is unprecedented in few‐shot object detection. We have designed FRHead, which is the first to introduce closed‐form solution‐based feature reconstruction [30–34] for few‐shot object detection. FRHead utilizes feature reconstruction to obtain a more comprehensive metric of feature maps, rather than classifying through dimensionality reduction regression.…”

Section: Introductionmentioning

confidence: 99%

FRDet: Few‐shot object detection via feature reconstruction

Chen

Mao

Qian

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

State‐of‐the‐art object detection models rely on large‐scale datasets for training to achieve good precision. Without sufficient samples, the model can suffer from severe overfitting. Current explorations in few‐shot object detection are mainly divided into meta‐learning‐based methods and fine‐tuning‐based methods. However, existing models do not focus on how feature maps should be processed to present more accurate regions of interest (RoIs), leading to many non‐supporting RoIs. These non‐supporting RoIs can increase the burden of subsequent classification and even lead to misclassification. Additionally, catastrophic forgetting is inevitable in both few‐shot object detection models. Many models classify directly in low‐dimensional spaces due to insufficient resources, but this transformation of the data space can confuse some categories and lead to misclassification. To address these problems, the Feature Reconstruction Detector (FRDet) is proposed, a simple yet effective fine‐tune‐based approach for few‐shot object detection. FRDet includes a region proposal network (RPN) based on channel attention and space attention called Multi‐Attention RPN (MARPN) and a head based on feature reconstruction called Feature Reconstruction Head (FRHead). MARPN utilizes channel attention to suppress non‐supporting classes and spatial attention to enhance support classes based on Attention RPN, resulting in fewer but more accurate RoIs. Meanwhile, FRHead utilizes support features to reconstruct query RoI features through a closed‐form solution, allowing for a comprehensive and fine‐grained comparison. The model was validated on the PASCAL VOC, MS COCO, FSOD, and CUB200 datasets and achieved better results.

show abstract

“…Chen et al [39] proposed P2Net based on contrast learning, which uses a two-branch network and an image aggregation module to achieve good fine-grained classification performance. Li et al [40] proposed a foreground aware Feature Pyramid Network (FPN) network for the small sample problem. They proposed two methods for computing foreground weights to effectively solve the fine-grained classification problem of ships in the small sample case.…”

Section: Fine-grained Ship Classificationmentioning

confidence: 99%

Fine-Grained Classification of Remote Sensing Ship Images Based on Improved VAN

Zhou,

Huang,

Sun

2023

CMC

View full text Add to dashboard Cite

The remote sensing ships' fine-grained classification technology makes it possible to identify certain ship types in remote sensing images, and it has broad application prospects in civil and military fields. However, the current model does not examine the properties of ship targets in remote sensing images with mixed multi-granularity features and a complicated backdrop. There is still an opportunity for future enhancement of the classification impact. To solve the challenges brought by the above characteristics, this paper proposes a Metaformer and Residual fusion network based on Visual Attention Network (VAN-MR) for fine-grained classification tasks. For the complex background of remote sensing images, the VAN-MR model adopts the parallel structure of large kernel attention and spatial attention to enhance the model's feature extraction ability of interest targets and improve the classification performance of remote sensing ship targets. For the problem of multi-grained feature mixing in remote sensing images, the VAN-MR model uses a Metaformer structure and a parallel network of residual modules to extract ship features. The parallel network has different depths, considering both high-level and lowlevel semantic information. The model achieves better classification performance in remote sensing ship images with multi-granularity mixing. Finally, the model achieves 88.73% and 94.56% accuracy on the public fine-grained ship collection-23 (FGSC-23) and FGSCR-42 datasets, respectively, while the parameter size is only 53.47 M, the floating point operations is 9.9 G. The experimental results show that the classification effect of VAN-MR is superior to that of traditional CNNs model and visual model with Transformer structure under the same parameter quantity.

show abstract

Few-Shot Fine-Grained Ship Classification With a Foreground-Aware Feature Map Reconstruction Network

Cited by 17 publications

References 24 publications

Vessel classification algorithm based on the convolutional attention module for natural maritime images

Vessel classification algorithm based on the convolutional attention module for natural maritime images

FRDet: Few‐shot object detection via feature reconstruction

Fine-Grained Classification of Remote Sensing Ship Images Based on Improved VAN

Contact Info

Product

Resources

About