Towards Backward-Compatible Representation Learning

03/26/2020
by   Yantao Shen, et al.
4

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/06/2021

Forward Compatible Training for Representation Learning

In visual retrieval systems, updating the embedding model requires recom...
research
03/03/2022

Towards Universal Backward-Compatible Representation Learning

Conventional model upgrades for visual search systems require offline re...
research
08/07/2021

Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation

In object re-identification (ReID), the development of deep learning tec...
research
08/04/2021

Learning Compatible Embeddings

Achieving backward compatibility when rolling out new models can highly ...
research
11/15/2021

CoReS: Compatible Representations via Stationarity

In this paper, we propose a novel method to learn internal feature repre...
research
06/07/2022

Learning Backward Compatible Embeddings

Embeddings, low-dimensional vector representation of objects, are fundam...
research
04/08/2020

Training Neural Networks to Produce Compatible Features

This paper makes a first step towards compatible and hence reusable netw...

Please sign up or login with your details

Forgot password? Click here to reset