Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhuo, Wei, Luo, Runjie, Xue, Wufeng, Shen, Linlin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908470023815168
author Zhuo, Wei
Luo, Runjie
Xue, Wufeng
Shen, Linlin
author_facet Zhuo, Wei
Luo, Runjie
Xue, Wufeng
Shen, Linlin
contents Few-shot Learning (FSL), which endeavors to develop the generalization ability for recognizing novel classes using only a few images, faces significant challenges due to data scarcity. Recent CLIP-like methods based on contrastive language-image pertaining mitigate the issue by leveraging textual representation of the class name for unseen image discovery. Despite the achieved success, simply aligning visual representations to class name embeddings would compromise the visual diversity for novel class discrimination. To this end, we proposed a novel Few-Shot Learning (FSL) method (BCT-CLIP) that explores \textbf{dominating properties} via contrastive learning beyond simply using class tokens. Through leveraging LLM-based prior knowledge, our method pushes forward FSL with comprehensive structural image representations, including both global category representation and the patch-aware property embeddings. In particular, we presented a novel multi-property generator (MPG) with patch-aware cross-attentions to generate multiple visual property tokens, a Large-Language Model (LLM)-assistant retrieval procedure with clustering-based pruning to obtain dominating property descriptions, and a new contrastive learning strategy for property-token learning. The superior performances on the 11 widely used datasets demonstrate that our investigation of dominating properties advances discriminative class-specific representation learning and few-shot classification.
format Preprint
id arxiv_https___arxiv_org_abs_2507_20511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification
Zhuo, Wei
Luo, Runjie
Xue, Wufeng
Shen, Linlin
Computer Vision and Pattern Recognition
Few-shot Learning (FSL), which endeavors to develop the generalization ability for recognizing novel classes using only a few images, faces significant challenges due to data scarcity. Recent CLIP-like methods based on contrastive language-image pertaining mitigate the issue by leveraging textual representation of the class name for unseen image discovery. Despite the achieved success, simply aligning visual representations to class name embeddings would compromise the visual diversity for novel class discrimination. To this end, we proposed a novel Few-Shot Learning (FSL) method (BCT-CLIP) that explores \textbf{dominating properties} via contrastive learning beyond simply using class tokens. Through leveraging LLM-based prior knowledge, our method pushes forward FSL with comprehensive structural image representations, including both global category representation and the patch-aware property embeddings. In particular, we presented a novel multi-property generator (MPG) with patch-aware cross-attentions to generate multiple visual property tokens, a Large-Language Model (LLM)-assistant retrieval procedure with clustering-based pruning to obtain dominating property descriptions, and a new contrastive learning strategy for property-token learning. The superior performances on the 11 widely used datasets demonstrate that our investigation of dominating properties advances discriminative class-specific representation learning and few-shot classification.
title Beyond Class Tokens: LLM-guided Dominant Property Mining for Few-shot Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.20511