Multi-level Similarity Learning for Low-Shot Recognition

12/13/2019
by   Hongwei Xv, et al.
41

Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence. According to this concept, we propose a multi-level similarity model (MLSM) to capture the deep encoded distance metric between the support and query samples. Our approach is achieved based on the fact that the image similarity learning can be decomposed into image-level, global-level, and object-level. Once the similarity function is established, MLSM will be able to classify images for unseen classes by computing the similarity scores between a limited number of labeled samples and the target images. Furthermore, we conduct 5-way experiments with both 1-shot and 5-shot setting on Caltech-UCSD datasets. It is demonstrated that the proposed model can achieve promising results compared with the existing methods in practical applications.

READ FULL TEXT

page 1

page 3

page 4

page 5

research
03/21/2021

Multi-level Metric Learning for Few-shot Image Recognition

Few-shot learning is devoted to training a model on few samples. Recentl...
research
04/09/2023

RD-DPP: Rate-Distortion Theory Meets Determinantal Point Process to Diversify Learning Data Samples

In some practical learning tasks, such as traffic video analysis, the nu...
research
10/20/2020

Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples

Predictive modeling is useful but very challenging in biological image a...
research
05/28/2018

Object-Level Representation Learning for Few-Shot Image Classification

Few-shot learning that trains image classifiers over few labeled example...
research
12/09/2020

Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity

Few-shot classifiers excel under limited training samples, making it use...
research
11/28/2019

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

The main problems of few-shot learning are how to learn a generalized re...
research
09/21/2021

Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications

Automatic classification of pests and plants (both healthy and diseased)...

Please sign up or login with your details

Forgot password? Click here to reset