Task-Aware Few-Shot Visual Classification with Improved Self-Supervised Metric Learning

Few-shot learning strategies are developed for training a reliable model on even a limited amount of data, but few-shot learning tasks usually lead to the over-fitting dilemma and result in a task-level inductive bias. In contrast to conventional few-shot learning techniques following the meta-learn...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng, Chia-Sheng, Shao, Hao-Chiang, Lin, Chia-Wen
Format: Conference Proceeding
Language:English
Subjects:
Feature extraction
few-shot learning
Measurement
metric learning
Reliability engineering
Self-supervised learning
Training
Transforms
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Few-shot learning strategies are developed for training a reliable model on even a limited amount of data, but few-shot learning tasks usually lead to the over-fitting dilemma and result in a task-level inductive bias. In contrast to conventional few-shot learning techniques following the meta-learning framework design, recent few-shot learning studies aim to derive a reliable feature extractors via a self-supervised learning mechanism for solving the dilemma. Therefore, we proposed in this paper a task-aware few-shot visual classification framework by articulating meta-learning, traditional supervised classification, and self-supervised learning schemes. The proposed mechanism learns to transform an initial feature embedding into a more general and representative space so that classification performance can be boosted. Extensive experiments show that the proposed method can solve the over-fitting dilemma and outperforms previous state-of-the-art few-shot learning methods.
ISSN:2381-8549
DOI:10.1109/ICIP46576.2022.9897878