Layer-Wise Adaptive Updating for Few-Shot Image Classification

07/16/2020
by   Yunxiao Qin, et al.
0

Few-shot image classification (FSIC), which requires a model to recognize new categories via learning from few images of these categories, has attracted lots of attention. Recently, meta-learning based methods have been shown as a promising direction for FSIC. Commonly, they train a meta-learner (meta-learning model) to learn easy fine-tuning weight, and when solving an FSIC task, the meta-learner efficiently fine-tunes itself to a task-specific model by updating itself on few images of the task. In this paper, we propose a novel meta-learning based layer-wise adaptive updating (LWAU) method for FSIC. LWAU is inspired by an interesting finding that compared with common deep models, the meta-learner pays much more attention to update its top layer when learning from few images. According to this finding, we assume that the meta-learner may greatly prefer updating its top layer to updating its bottom layers for better FSIC performance. Therefore, in LWAU, the meta-learner is trained to learn not only the easy fine-tuning model but also its favorite layer-wise adaptive updating rule to improve its learning efficiency. Extensive experiments show that with the layer-wise adaptive updating rule, the proposed LWAU: 1) outperforms existing few-shot classification methods with a clear margin; 2) learns from few images more efficiently by at least 5 times than existing meta-learners when solving FSIC.

READ FULL TEXT
research
06/03/2022

MetaLR: Layer-wise Learning Rate based on Meta-Learning for Adaptively Fine-tuning Medical Pre-trained Models

When applying transfer learning for medical image analysis, downstream t...
research
11/19/2018

Representation based and Attention augmented Meta learning

Deep learning based computer vision fails to work when labeled images ar...
research
02/22/2021

MetaDelta: A Meta-Learning System for Few-shot Image Classification

Meta-learning aims at learning quickly on novel tasks with limited data ...
research
12/11/2018

Rethink and Redesign Meta learning

Recently, Meta-learning has been shown as a promising way to improve the...
research
07/13/2020

Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification

Deep neural networks are highly effective when a large number of labeled...
research
05/13/2019

Few-Shot Viewpoint Estimation

Viewpoint estimation for known categories of objects has been improved s...
research
02/22/2021

Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce

Product title compression for voice and mobile commerce is a well studie...

Please sign up or login with your details

Forgot password? Click here to reset