Hard Negative Mining for Metric Learning Based Zero-Shot Classification

08/26/2016
by   Maxime Bucher, et al.
0

Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/27/2016

Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classification

This paper addresses the task of zero-shot image classification. The key...
research
09/10/2019

Semantic Similarity Based Softmax Classifier for Zero-Shot Learning

Zero-Shot Learning (ZSL) is a classification task where we do not have e...
research
04/02/2020

ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis

We consider the problem of distance metric learning (DML), where the tas...
research
08/07/2019

Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings

Learning an effective similarity measure between image representations i...
research
07/19/2018

Selective Zero-Shot Classification with Augmented Attributes

In this paper, we introduce a selective zero-shot classification problem...
research
10/27/2022

A few-shot learning approach with domain adaptation for personalized real-life stress detection in close relationships

We design a metric learning approach that aims to address computational ...
research
07/27/2019

Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval

In zero-shot image retrieval (ZSIR) task, embedding learning becomes mor...

Please sign up or login with your details

Forgot password? Click here to reset