Supervised Metric Learning for Retrieval via Contextual Similarity Optimization

10/04/2022
by   Christopher Liao, et al.
0

Existing deep metric learning approaches fall into three general categories: contrastive learning, average precision (AP) maximization, and classification. We propose a novel alternative approach, contextual similarity optimization, inspired by work in unsupervised metric learning. Contextual similarity is a discrete similarity measure based on relationships between neighborhood sets, and is widely used in the unsupervised setting as pseudo-supervision. Inspired by this success, we propose a framework which optimizes a combination of contextual and cosine similarities. Contextual similarity calculation involves several non-differentiable operations, including the heaviside function and intersection of sets. We show how to circumvent non-differentiability to explicitly optimize contextual similarity, and we further incorporate appropriate similarity regularization to yield our novel metric learning loss. The resulting loss function achieves state-of-the-art Recall @ 1 accuracy on standard supervised image retrieval benchmarks when combined with the standard contrastive loss. Code is released here: <https://github.com/Chris210634/metric-learning-using-contextual-similarity>

READ FULL TEXT
research
05/09/2022

Introspective Deep Metric Learning

This paper proposes an introspective deep metric learning (IDML) framewo...
research
07/08/2021

Case-based similar image retrieval for weakly annotated large histopathological images of malignant lymphoma using deep metric learning

In the present study, we propose a novel case-based similar image retrie...
research
12/27/2016

End-to-End Data Visualization by Metric Learning and Coordinate Transformation

This paper presents a deep nonlinear metric learning framework for data ...
research
11/16/2019

Unsupervised Deep Metric Learning via Auxiliary Rotation Loss

Deep metric learning is an important area due to its applicability to ma...
research
10/11/2022

Large-to-small Image Resolution Asymmetry in Deep Metric Learning

Deep metric learning for vision is trained by optimizing a representatio...
research
09/20/2019

Deep Metric Learning using Similarities from Nonlinear Rank Approximations

In recent years, deep metric learning has achieved promising results in ...
research
10/23/2020

Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning

Image-based 3D shape retrieval (IBSR) aims to find the corresponding 3D ...

Please sign up or login with your details

Forgot password? Click here to reset