Sparse spatial transformers for few-shot learning

Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have recently addressed this challenge using deep descriptors and...

Full description

Saved in:
Bibliographic Details
Published in:Science China. Information sciences 2023-11, Vol.66 (11), p.210102, Article 210102
Main Authors: Chen, Haoxing, Li, Huaxiong, Li, Yaohui, Chen, Chunlin
Format: Article
Language:English
Subjects:
Algorithms
Computer Science
Information Systems and Communication Service
Learning
Neural networks
Optimization
Prototypes
Representations
Research Paper
Teaching methods
Transformers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Learning from limited data is challenging because data scarcity leads to a poor generalization of the trained model. A classical global pooled representation will probably lose useful local information. Many few-shot learning methods have recently addressed this challenge using deep descriptors and learning a pixel-level metric. However, using deep descriptors as feature representations may lose image contextual information. Moreover, most of these methods independently address each class in the support set, which cannot sufficiently use discriminative information and task-specific embeddings. In this paper, we propose a novel transformer-based neural network architecture called sparse spatial transformers (SSFormers), which finds task-relevant features and suppresses task-irrelevant features. Particularly, we first divide each input image into several image patches of different sizes to obtain dense local features. These features retain contextual information while expressing local information. Then, a sparse spatial transformer layer is proposed to find spatial correspondence between the query image and the full support set to select task-relevant image patches and suppress task-irrelevant image patches. Finally, we propose using an image patch-matching module to calculate the distance between dense local representations, thus determining which category the query image belongs to in the support set. Extensive experiments on popular few-shot learning benchmarks demonstrate the superiority of our method over state-of-the-art methods.
ISSN:1674-733X
1869-1919
DOI:10.1007/s11432-022-3700-8