All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning

11/28/2019
by   Shaoli Huang, et al.
22

The main problems of few-shot learning are how to learn a generalized representation and how to construct discriminant classifiers with few-shot samples. We tackle both issues by learning a multi-level representation with a classifier-centric constraint. We first build the multi-level representation by combining three different levels of information: local, global, and higher-level. The resulting representation can characterize new concepts with different aspects and present more universality. To overcome the difficulty of generating classifiers by several shot features, we also propose a classifier-centric loss for learning the representation of each level, which forces samples to be centered on their respective classifier weights in the feature space. Therefore, the multi-level representation learned with classifier-centric constraint not only can enhance the generalization ability, but also can be used to construct the discriminant classifier through a small number of samples. Experiments show that our proposed method, without training or fine-tuning on novel examples, can outperform the current state-of-the-art methods on two low-shot learning datasets. We further show that our approach achieves a significant improvement over baseline method in cross-task validation, and demonstrate its superiority in alleviating the domain shift problem.

READ FULL TEXT

page 1

page 2

page 7

research
05/28/2021

One-shot Learning with Absolute Generalization

One-shot learning is proposed to make a pretrained classifier workable o...
research
07/22/2022

Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence

Gathering cyber threat intelligence from open sources is becoming increa...
research
02/14/2021

Multi-Level Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data

In scientific machine learning, regression networks have been recently a...
research
07/08/2020

Predicting the Accuracy of a Few-Shot Classifier

In the context of few-shot learning, one cannot measure the generalizati...
research
12/13/2019

Multi-level Similarity Learning for Low-Shot Recognition

Low-shot learning indicates the ability to recognize unseen objects base...
research
03/24/2022

A Rationale-Centric Framework for Human-in-the-loop Machine Learning

We present a novel rationale-centric framework with human-in-the-loop – ...
research
08/21/2020

Spatial Language Representation with Multi-Level Geocoding

We present a multi-level geocoding model (MLG) that learns to associate ...

Please sign up or login with your details

Forgot password? Click here to reset