Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity

Guo, Yurong; Du, Ruoyi; Li, Xiaoxu; Xie, Jiyang; Ma, Zhanyu; Dong, Yuan

doi:10.1109/tip.2022.3184813

Cited by 42 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In several fields, such as image classification and image segmentation, the CNN methods have gained enormous success (Zhao et al, 2021 , 2023 ; Guo et al, 2022 ). Traditional segmentation methods generally use convolutional and pooling layers to extract local features and thus perform segmentation (Li et al, 2021 ).…”

Section: Related Workmentioning

confidence: 99%

TransRender: a transformer-based boundary rendering segmentation network for stroke lesions

Wu,

Zhang,

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

Vision transformer architectures attract widespread interest due to their robust representation capabilities of global features. Transformer-based methods as the encoder achieve superior performance compared to convolutional neural networks and other popular networks in many segmentation tasks for medical images. Due to the complex structure of the brain and the approximate grayscale of healthy tissue and lesions, lesion segmentation suffers from over-smooth boundaries or inaccurate segmentation. Existing methods, including the transformer, utilize stacked convolutional layers as the decoder to uniformly treat each pixel as a grid, which is convenient for feature computation. However, they often neglect the high-frequency features of the boundary and focus excessively on the region features. We propose an effective method for lesion boundary rendering called TransRender, which adaptively selects a series of important points to compute the boundary features in a point-based rendering way. The transformer-based method is selected to capture global information during the encoding stage. Several renders efficiently map the encoded features of different levels to the original spatial resolution by combining global and local features. Furthermore, the point-based function is employed to supervise the render module generating points, so that TransRender can continuously refine the uncertainty region. We conducted substantial experiments on different stroke lesion segmentation datasets to prove the efficiency of TransRender. Several evaluation metrics illustrate that our method can automatically segment the stroke lesion with relatively high accuracy and low calculation complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

TransRender: a transformer-based boundary rendering segmentation network for stroke lesions

Wu,

Zhang,

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Research interest in the field of similarity analysis continues in many areas such as Clustering [ 21 , 22 , 23 , 24 ], Classification [ 25 , 26 , 27 , 28 ], and Recommendation systems [ 29 , 30 , 31 , 32 , 33 ]. In data stream analysis, Similarity has many recent research articles as well [ 34 , 35 , 36 , 37 , 38 , 39 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Similarity-Based Adaptive Window for Improving Classification of Epileptic Seizures with Imbalance EEG Data Stream

Fatlawi

Kiss

2022

Entropy

View full text Add to dashboard Cite

Data stream mining techniques have recently received increasing research interest, especially in medical data classification. An unbalanced representation of the classification’s targets in these data is a common challenge because classification techniques are biased toward the major class. Many methods have attempted to address this problem but have been exaggeratedly biased toward the minor class. In this work, we propose a method for balancing the presence of the minor class within the current window of the data stream while preserving the data’s original majority as much as possible. The proposed method utilized similarity analysis for selecting specific instances from the previous window. This group of minor-class was then added to the current window’s instances. Implementing the proposed method using the Siena dataset showed promising results compared to the Skew ensemble method and some other research methods.

show abstract

“…Dong et al [25] used the back-end network to extract multilevel feature information from the base class and improved the loss function to maximize the distance between different categories and minimize the distance between the same categories in few-shot learning. Guo et al [26] introduced the pairwise similarity module into few-shot learning and generated the calibrated class centres suitable for the query sample by extracting the semantic correlations between the support and query sample and enhancing the discriminant regions. It is clear that few-shot learning has great potential to address pavement texture recognition issues.…”

Section: Introductionmentioning

confidence: 99%

“…Guo et al . [ 26 ] introduced the pairwise similarity module into few-shot learning and generated the calibrated class centres suitable for the query sample by extracting the semantic correlations between the support and query sample and enhancing the discriminant regions. It is clear that few-shot learning has great potential to address pavement texture recognition issues.…”

Section: Introductionmentioning

confidence: 99%

Automatic pavement texture recognition using lightweight few-shot learning

Shuo

Yan

Liu

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Texture is a crucial characteristic of roads, closely related to their performance. The recognition of pavement texture is of great significance for road maintenance professionals to detect potential safety hazards and carry out necessary countermeasures. Although deep learning models have been applied for recognition, the scarcity of data has always been a limitation. To address this issue, this paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition with a limited dataset. The model achieved 89.8% accuracy in a four-way five-shot task classifying the pavement textures of dense asphalt concrete, micro surface, open-graded friction course and stone matrix asphalt. To align with engineering practice, global average pooling (GAP) and one-dimensional convolution are implemented, creating lightweight models that save storage and training time. Comparative experiments show that the lightweight model with GAP implemented on dense layers and one-dimensional convolution on convolutional layers reduced storage volume by 94% and training time by 99%, despite a 2.9% decrease in classification accuracy. Moreover, the model with only GAP implemented on dense layers achieved the highest accuracy at 93.5%, while reducing storage volume and training time by 83% and 6%, respectively. This article is part of the theme issue 'Artificial intelligence in failure analysis of transportation infrastructure and materials'.

show abstract

Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity

Cited by 42 publications

References 47 publications

TransRender: a transformer-based boundary rendering segmentation network for stroke lesions

TransRender: a transformer-based boundary rendering segmentation network for stroke lesions

Similarity-Based Adaptive Window for Improving Classification of Epileptic Seizures with Imbalance EEG Data Stream

Automatic pavement texture recognition using lightweight few-shot learning

Contact Info

Product

Resources

About