Cross-Domain Few-Shot Classification based on Lightweight Res2Net and Flexible GNN

Chen, Yu; Zheng, Yunan; Xu, Zhenyu; Tang, Tianhang; Tang, Zixin; Chen, Jie; Liu, Yiguang

doi:10.1016/j.knosys.2022.108623

Cited by 15 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They constructed a selective-comparison similarity module (SCSM) based on pyramid structure and attention mechanism to assign different weights to the background and target, aiming to produce multi-scaled feature maps for classification. In [30], they were the first to attempt integrating the idea of multi-scale representation into the cross-domain few-shot classification problem by proposing a new hierarchical residuallike block applicable to lightweight ResNet structures such as ResNet-10. In [31], Zhang et al proposed a multi-scale second-order relation network (MsSoSN), which equipped second-order pooling and a scale selector to create multi-scale second-order representations.…”

Section: Metric-based Local And/or Global Deep Feature Representation...mentioning

confidence: 99%

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

Ren,

Li,

et al. 2024

View full text Add to dashboard Cite

Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of images (e.g., birds, flowers, and airplanes) belonging to different subclasses of the same species by a small number of labeled samples. Through feature representation learning, FSFGIC methods can make better use of limited sample information, learn more discriminative feature representations, greatly improve the classification accuracy and generalization ability, and thus achieve better results in FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local and/or global deep feature representation learning, class representation learning, and task-specific feature representation learning). In addition, the existing popular datasets, current challenges and future development trends of feature representation learning on FSFGIC are also described.

show abstract

Section: Metric-based Local And/or Global Deep Feature Representation...mentioning

confidence: 99%

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

Ren,

Li,

et al. 2024

View full text Add to dashboard Cite

show abstract

“…[120] proposes a diversified feature transformation based on the original feature transformation layer to solve the CDFSL problem. And [11] offer two new strategies, FGNN (Flexible GNN) and a new hierarchical residual-like block, for the encoder and metric function of the metric-based network. To achieve this, researchers have proposed various methods.…”

Section: Parameter Freezementioning

confidence: 99%

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

Xu¹,

Zhi²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning has been highly successful in computer vision with large amounts of labeled data, but struggles with limited labeled training data. To address this, Few-shot learning (FSL) is proposed, but it assumes that all samples (including source and target task data, where target tasks are performed with prior knowledge from source ones) are from the same domain, which is a stringent assumption in the real world. To alleviate this limitation, Cross-domain few-shot learning (CDFSL) has gained attention as it allows source and target data from different domains and label spaces. This paper provides a comprehensive review of CDFSL at the first time, which has received far less attention than FSL due to its unique setup and difficulties. We expect this paper to serve as both a position paper and a tutorial for those doing research in CDFSL. This review first introduces the definition of CDFSL and the issues involved, followed by the core scientific question and challenge. A comprehensive review of validated CDFSL approaches from the existing literature is then presented, along with their detailed descriptions based on a rigorous taxonomy. Furthermore, this paper outlines and discusses several promising directions of CDFSL that deserve further scientific investigation, covering aspects of problem setups, applications and theories.

show abstract

“…In deep learning tasks, the training and test data are typically derived from the same dataset. However, in practical applications, the source and target data may be sampled separately, or the training and test environments may vary, leading to the cross-domain problem [ 8 ]. The cross-domain problem refers to the difference between the source domain and target domain in terms of feature space, category space, or edge distribution, which affects the model’s generalization performance in the target domain.…”

Section: Introductionmentioning

confidence: 99%

Research on a Cross-Domain Few-Shot Adaptive Classification Algorithm Based on Knowledge Distillation Technology

Gao,

Li,

Xia

et al. 2024

Sensors

View full text Add to dashboard Cite

With the development of deep learning and sensors and sensor collection methods, computer vision inspection technology has developed rapidly. The deep-learning-based classification algorithm requires the acquisition of a model with superior generalization capabilities through the utilization of a substantial quantity of training samples. However, due to issues such as privacy, annotation costs, and sensor-captured images, how to make full use of limited samples has become a major challenge for practical training and deployment. Furthermore, when simulating models and transferring them to actual image scenarios, discrepancies often arise between the common training sets and the target domain (domain offset). Currently, meta-learning offers a promising solution for few-shot learning problems. However, the quantity of supporting set data on the target domain remains limited, leading to limited cross-domain learning effectiveness. To address this challenge, we have developed a self-distillation and mixing (SDM) method utilizing a Teacher–Student framework. This method effectively transfers knowledge from the source domain to the target domain by applying self-distillation techniques and mixed data augmentation, learning better image representations from relatively abundant datasets, and achieving fine-tuning in the target domain. In comparison with nine classical models, the experimental results demonstrate that the SDM method excels in terms of training time and accuracy. Furthermore, SDM effectively transfers knowledge from the source domain to the target domain, even with a limited number of target domain samples.

show abstract

Cross-Domain Few-Shot Classification based on Lightweight Res2Net and Flexible GNN

Cited by 15 publications

References 8 publications

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

Few-Shot Fine-Grained Image Classification: A Comprehensive Review

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

Research on a Cross-Domain Few-Shot Adaptive Classification Algorithm Based on Knowledge Distillation Technology

Contact Info

Product

Resources

About