Disentangled Feature Representation for Few-shot Image Classification

09/26/2021
by   Hao Cheng, et al.
0

Learning the generalizable feature representation is critical for few-shot image classification. While recent works exploited task-specific feature embedding using meta-tasks for few-shot learning, they are limited in many challenging tasks as being distracted by the excursive features such as the background, domain and style of the image samples. In this work, we propose a novel Disentangled Feature Representation framework, dubbed DFR, for few-shot learning applications. DFR can adaptively decouple the discriminative features that are modeled by the classification branch, from the class-irrelevant component of the variation branch. In general, most of the popular deep few-shot learning methods can be plugged in as the classification branch, thus DFR can boost their performance on various few-shot tasks. Furthermore, we propose a novel FS-DomainNet dataset based on DomainNet, for benchmarking the few-shot domain generalization tasks. We conducted extensive experiments to evaluate the proposed DFR on general and fine-grained few-shot classification, as well as few-shot domain generalization, using the corresponding four benchmarks, i.e., mini-ImageNet, tiered-ImageNet, CUB, as well as the proposed FS-DomainNet. Thanks to the effective feature disentangling, the DFR-based few-shot classifiers achieved the state-of-the-art results on all datasets.

READ FULL TEXT
research
09/14/2021

One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification

Real-world classification tasks are frequently required to work in an op...
research
02/18/2023

An Adaptive Plug-and-Play Network for Few-Shot Learning

Few-shot learning (FSL) requires a model to classify new samples after l...
research
08/09/2021

Transductive Few-Shot Classification on the Oblique Manifold

Few-shot learning (FSL) attempts to learn with limited data. In this wor...
research
02/05/2022

Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approach

Few-shot learning (FSL) is the process of rapid generalization from abun...
research
05/10/2022

Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling

Every day, a new method is published to tackle Few-Shot Image Classifica...
research
03/20/2020

Selecting Relevant Features from a Universal Representation for Few-shot Classification

Popular approaches for few-shot classification consist of first learning...
research
11/29/2022

Disentangled Generation with Information Bottleneck for Few-Shot Learning

Few-shot learning (FSL), which aims to classify unseen classes with few ...

Please sign up or login with your details

Forgot password? Click here to reset