Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?

03/08/2018
by   Nam Vo, et al.
0

Many recent works advancing deep learning tend to focus on large scale setting with the goal of more effective training and better fitting. This goal might be less applicable to the case of small to medium scale. Studying deep metric learning under such setting, we reason that better generalization could be a big contributing factor to improvement of previous works, as well as the goal for further improvement. We investigate using other layers in a deep metric learning system (beside the embedding layer) for feature extraction and analyze how well they perform on training data and generalize to testing data. From this study, we suggest a new regularization practice and demonstrate state-of-the-art performance on 3 fine-grained image retrieval benchmarks: Cars-196, CUB-200-2011 and Stanford Online Product.

READ FULL TEXT
research
04/30/2020

DIABLO: Dictionary-based Attention Block for Deep Metric Learning

Recent breakthroughs in representation learning of unseen classes and ex...
research
01/22/2019

Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering

Deep metric learning has been widely applied in many computer vision tas...
research
02/08/2021

Multi-level Distance Regularization for Deep Metric Learning

We propose a novel distance-based regularization method for deep metric ...
research
08/13/2018

Deep Randomized Ensembles for Metric Learning

Learning embedding functions, which map semantically related inputs to n...
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
03/31/2021

Learning with Memory-based Virtual Classes for Deep Metric Learning

The core of deep metric learning (DML) involves learning visual similari...
research
06/23/2023

Catching Image Retrieval Generalization

The concepts of overfitting and generalization are vital for evaluating ...

Please sign up or login with your details

Forgot password? Click here to reset