DeepAI AI Chat
Log In Sign Up

Instance-level Few-shot Learning with Class Hierarchy Mining

by   Anh-Khoa Nguyen Vu, et al.
University of Dayton
Monash University

Few-shot learning is proposed to tackle the problem of scarce training data in novel classes. However, prior works in instance-level few-shot learning have paid less attention to effectively utilizing the relationship between categories. In this paper, we exploit the hierarchical information to leverage discriminative and relevant features of base classes to effectively classify novel objects. These features are extracted from abundant data of base classes, which could be utilized to reasonably describe classes with scarce data. Specifically, we propose a novel superclass approach that automatically creates a hierarchy considering base and novel classes as fine-grained classes for few-shot instance segmentation (FSIS). Based on the hierarchical information, we design a novel framework called Soft Multiple Superclass (SMS) to extract relevant features or characteristics of classes in the same superclass. A new class assigned to the superclass is easier to classify by leveraging these relevant features. Besides, in order to effectively train the hierarchy-based-detector in FSIS, we apply the label refinement to further describe the associations between fine-grained classes. The extensive experiments demonstrate the effectiveness of our method on FSIS benchmarks. Code is available online.


page 1

page 7

page 9

page 10


Compositional Fine-Grained Low-Shot Learning

We develop a novel compositional generative model for zero- and few-shot...

PatchMix Augmentation to Identify Causal Features in Few-shot Learning

The task of Few-shot learning (FSL) aims to transfer the knowledge learn...

Incremental Few-Shot Instance Segmentation

Few-shot instance segmentation methods are promising when labeled traini...

Variational Transfer Learning for Fine-grained Few-shot Visual Recognition

Fine-grained few-shot recognition often suffers from the problem of trai...

Disentangled Generation with Information Bottleneck for Few-Shot Learning

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

Few-shot Image Recognition with Manifolds

In this paper, we extend the traditional few-shot learning (FSL) problem...

MDFM: Multi-Decision Fusing Model for Few-Shot Learning

In recent years, researchers pay growing attention to the few-shot learn...