tSF: Transformer-based Semantic Filter for Few-Shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lai, Jinxiang, Yang, Siqian, Liu, Wenlong, Zeng, Yi, Huang, Zhongyi, Wu, Wenlong, Liu, Jun, Gao, Bin-Bin, Wang, Chengjie
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914873476120576
author Lai, Jinxiang
Yang, Siqian
Liu, Wenlong
Zeng, Yi
Huang, Zhongyi
Wu, Wenlong
Liu, Jun
Gao, Bin-Bin
Wang, Chengjie
author_facet Lai, Jinxiang
Yang, Siqian
Liu, Wenlong
Zeng, Yi
Huang, Zhongyi
Wu, Wenlong
Liu, Jun
Gao, Bin-Bin
Wang, Chengjie
contents Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples. Most feature embedding modules in recent FSL methods are specially designed for corresponding learning tasks (e.g., classification, segmentation, and object detection), which limits the utility of embedding features. To this end, we propose a light and universal module named transformer-based Semantic Filter (tSF), which can be applied for different FSL tasks. The proposed tSF redesigns the inputs of a transformer-based structure by a semantic filter, which not only embeds the knowledge from whole base set to novel set but also filters semantic features for target category. Furthermore, the parameters of tSF is equal to half of a standard transformer block (less than 1M). In the experiments, our tSF is able to boost the performances in different classic few-shot learning tasks (about 2% improvement), especially outperforms the state-of-the-arts on multiple benchmark datasets in few-shot classification task.
format Preprint
id arxiv_https___arxiv_org_abs_2211_00868
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle tSF: Transformer-based Semantic Filter for Few-Shot Learning
Lai, Jinxiang
Yang, Siqian
Liu, Wenlong
Zeng, Yi
Huang, Zhongyi
Wu, Wenlong
Liu, Jun
Gao, Bin-Bin
Wang, Chengjie
Computer Vision and Pattern Recognition
Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples. Most feature embedding modules in recent FSL methods are specially designed for corresponding learning tasks (e.g., classification, segmentation, and object detection), which limits the utility of embedding features. To this end, we propose a light and universal module named transformer-based Semantic Filter (tSF), which can be applied for different FSL tasks. The proposed tSF redesigns the inputs of a transformer-based structure by a semantic filter, which not only embeds the knowledge from whole base set to novel set but also filters semantic features for target category. Furthermore, the parameters of tSF is equal to half of a standard transformer block (less than 1M). In the experiments, our tSF is able to boost the performances in different classic few-shot learning tasks (about 2% improvement), especially outperforms the state-of-the-arts on multiple benchmark datasets in few-shot classification task.
title tSF: Transformer-based Semantic Filter for Few-Shot Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.00868