ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Shi, Kexuan, Qi, Zhuang, Zhu, Jingjing, Meng, Lei, Zhang, Yaochen, Huang, Haibei, Meng, Xiangxu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916845327482880
author Shi, Kexuan
Qi, Zhuang
Zhu, Jingjing
Meng, Lei
Zhang, Yaochen
Huang, Haibei
Meng, Xiangxu
author_facet Shi, Kexuan
Qi, Zhuang
Zhu, Jingjing
Meng, Lei
Zhang, Yaochen
Huang, Haibei
Meng, Xiangxu
contents Open-set few-shot image classification aims to train models using a small amount of labeled data, enabling them to achieve good generalization when confronted with unknown environments. Existing methods mainly use visual information from a single image to learn class representations to distinguish known from unknown categories. However, these methods often overlook the benefits of integrating rich contextual information. To address this issue, this paper proposes a prototypical augmentation and alignment method, termed ProtoConNet, which incorporates background information from different samples to enhance the diversity of the feature space, breaking the spurious associations between context and image subjects in few-shot scenarios. Specifically, it consists of three main modules: the clustering-based data selection (CDS) module mines diverse data patterns while preserving core features; the contextual-enhanced semantic refinement (CSR) module builds a context dictionary to integrate into image representations, which boosts the model's robustness in various scenarios; and the prototypical alignment (PA) module reduces the gap between image representations and class prototypes, amplifying feature distances for known and unknown classes. Experimental results from two datasets verified that ProtoConNet enhances the effectiveness of representation learning in few-shot scenarios and identifies open-set samples, making it superior to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11845
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification
Shi, Kexuan
Qi, Zhuang
Zhu, Jingjing
Meng, Lei
Zhang, Yaochen
Huang, Haibei
Meng, Xiangxu
Computer Vision and Pattern Recognition
Open-set few-shot image classification aims to train models using a small amount of labeled data, enabling them to achieve good generalization when confronted with unknown environments. Existing methods mainly use visual information from a single image to learn class representations to distinguish known from unknown categories. However, these methods often overlook the benefits of integrating rich contextual information. To address this issue, this paper proposes a prototypical augmentation and alignment method, termed ProtoConNet, which incorporates background information from different samples to enhance the diversity of the feature space, breaking the spurious associations between context and image subjects in few-shot scenarios. Specifically, it consists of three main modules: the clustering-based data selection (CDS) module mines diverse data patterns while preserving core features; the contextual-enhanced semantic refinement (CSR) module builds a context dictionary to integrate into image representations, which boosts the model's robustness in various scenarios; and the prototypical alignment (PA) module reduces the gap between image representations and class prototypes, amplifying feature distances for known and unknown classes. Experimental results from two datasets verified that ProtoConNet enhances the effectiveness of representation learning in few-shot scenarios and identifies open-set samples, making it superior to existing methods.
title ProtoConNet: Prototypical Augmentation and Alignment for Open-Set Few-Shot Image Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.11845