A few-shot fine-grained image classification method leveraging global and local structures

Cao, Siyu; Wang, Wen; Zhang, Jing; Zheng, Min; Li, Qingyong

doi:10.1007/s13042-022-01522-w

Cited by 16 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the difference of contents and representations of learned features, the existing feature representation learning techniques for FSFGIC can be divided into three categories: local and/or global deep feature representation learning based FSFGIC methods [9,10], class representation learning based FSFGIC methods [11,12], and task-specific feature representation learning based FSFGIC methods [13,14]. According to different types of feature representation learning paradigms, a taxonomy of feature representation learning for FSFGIC methods is illustrated in Figure 2.…”

Section: A Taxonomy Of the Existing Feature Representation Learning F...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: A Taxonomy Of the Existing Feature Representation Learning F...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

“…To validate the efficiency of our method for fine-grained few-shot image classification, we conducted experiments on the three fine-grained image classification datasets discussed earlier. The results of Relation (Sung et al 2018), DN4 (Li et al 2019) and BSNet (Li et al 2021a) are from literature BSNet (Li et al 2021a), and the results of SAML (Hao et al 2019) and DeepEMD (Zhang et al 2020) are from DLG (Cao et al 2022), and the results of LRPABN (Huang et al 2021) are from MattML (Zhu, Liu, and Jiang 2020). The results of methods marked with †, such as ProtoNet (Snell, Swersky, and Zemel 2017), PARN (Wu et al 2019), CTX (Doersch, Gupta, and Zisserman 2020), FRN (Wertheimer, Tang, and Hariharan 2021), FRN+TDM (Lee, Moon, and Heo 2022) and Deep-EMD (Zhang et al 2020) provided by the author, which is replaced by the dataset used in this paper.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification

Chang

Sain

et al. 2023

AAAI

View full text Add to dashboard Cite

The main challenge for fine-grained few-shot image classification is to learn feature representations with higher inter-class and lower intra-class variations, with a mere few labelled samples. Conventional few-shot learning methods however cannot be naively adopted for this fine-grained setting -- a quick pilot study reveals that they in fact push for the opposite (i.e., lower inter-class variations and higher intra-class variations). To alleviate this problem, prior works predominately use a support set to reconstruct the query image and then utilize metric learning to determine its category. Upon careful inspection, we further reveal that such unidirectional reconstruction methods only help to increase inter-class variations and are not effective in tackling intra-class variations. In this paper, we for the first time introduce a bi-reconstruction mechanism that can simultaneously accommodate for inter-class and intra-class variations. In addition to using the support set to reconstruct the query set for increasing inter-class variations, we further use the query set to reconstruct the support set for reducing intra-class variations. This design effectively helps the model to explore more subtle and discriminative features which is key for the fine-grained problem in hand. Furthermore, we also construct a self-reconstruction module to work alongside the bi-directional module to make the features even more discriminative. Experimental results on three widely used fine-grained image classification datasets consistently show considerable improvements compared with other methods. Codes are available at: https://github.com/PRIS-CV/Bi-FRN.

show abstract

Dual adaptive local semantic alignment for few-shot fine-grained classification

Song,

Yang

2024

Vis Comput

View full text Add to dashboard Cite

A few-shot fine-grained image classification method leveraging global and local structures

Cited by 16 publications

References 18 publications

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

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

Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification

Dual adaptive local semantic alignment for few-shot fine-grained classification

Contact Info

Product

Resources

About