paper-with-me

홈 › Papers

LPN: Language-guided Prototypical Network for few-shot classification

2023-07-04 · Kaihui Cheng, Chule Yang, Xiao Liu, Naiyang Guan, Zhiyuan Wang

Few-shot classification aims to adapt to new tasks with limited labeled examples. To fully use the accessible data, recent methods explore suitable measures for the similarity between the query and support images and better high-dimensional features with meta-training and pre-training strategies. However, the potential of multi-modality information has barely been explored, which may bring promising improvement for few-shot classification. In this paper, we propose a Language-guided Prototypical Network (LPN) for few-shot classification, which leverages the complementarity of vision and language modalities via two parallel branches to improve the classifier. Concretely, to introduce language modality with limited samples in the visual task, we leverage a pre-trained text encoder to extract class-level text features directly from class names while processing images with a conventional image encoder. Then, we introduce a language-guided decoder to obtain text features corresponding to each image by aligning class-level features with visual features. Additionally, we utilize class-level features and prototypes to build a refined prototypical head, which generates robust prototypes in the text branch for follow-up measurement. Furthermore, we leverage the class-level features to align the visual features, capturing more class-relevant visual features. Finally, we aggregate the visual and text logits to calibrate the deviation of a single modality, enhancing the overall performance. Extensive experiments demonstrate the competitiveness of LPN against state-of-the-art methods on benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2307.01515

Code (0)

등록된 구현이 없습니다.

Tasks

Classification

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer

2022-01-14 · Yinyi Wei, Tong Mo, Yongtao Jiang, Weiping Li 외

Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label…

ClassificationContrastive LearningLanguage ModelingLanguage Modelling+3

Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detection

2025-12-17 · Yuxin Jiang, Yunkang Cao, Weiming Shen arxiv

Few-shot anomaly detection (FSAD) denotes the identification of anomalies within a target category with a limited number of normal samples. Existing FSAD methods largely rely on pre-trained feature representations to det…

Anomaly Detection

Gaussian Prototypical Networks for Few-Shot Learning on Omniglot

2017-08-09 · ICLR 2018 1 · Stanislav Fort

We propose a novel architecture for $k$-shot classification on the Omniglot dataset. Building on prototypical networks, we extend their architecture to what we call Gaussian prototypical networks. Prototypical networks l…

ClassificationClusteringFew-Shot LearningGeneral Classification

Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts

2025-06-05 · Zhong Ji, Rongshuai Wei, Jingren Liu, Yanwei Pang 외

Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samp…

Explainable ModelsFew-Shot Image Classificationimage-classificationImage Classification

Prototypical Priors: From Improving Classification to Zero-Shot Learning

2015-12-03 · Saumya Jetley, Bernardino Romera-Paredes, Sadeep Jayasumana, Philip Torr

Recent works on zero-shot learning make use of side information such as visual attributes or natural language semantics to define the relations between output visual classes and then use these relationships to draw infer…

ClassificationGeneral ClassificationZero-Shot Learning