Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval

by   Tan Pan, et al.

Image retrieval plays an important role in the Internet world. Usually, the core parts of mainstream visual retrieval systems include an online service of the embedding model and a large-scale vector database. For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data. Recently, backward-compatible training (BCT) enables the new model to be immediately deployed online by making the new embeddings directly comparable to the old ones. For BCT, improving the compatibility of two models with less negative impact on retrieval performance is the key challenge. In this paper, we introduce AdvBCT, an Adversarial Backward-Compatible Training method with an elastic boundary constraint that takes both compatibility and discrimination into consideration. We first employ adversarial learning to minimize the distribution disparity between embeddings of the new model and the old model. Meanwhile, we add an elastic boundary constraint during training to improve compatibility and discrimination efficiently. Extensive experiments on GLDv2, Revisited Oxford (ROxford), and Revisited Paris (RParis) demonstrate that our method outperforms other BCT methods on both compatibility and discrimination. The implementation of AdvBCT will be publicly available at


page 1

page 2

page 3

page 4


MixBCT: Towards Self-Adapting Backward-Compatible Training

The exponential growth of data, alongside advancements in model structur...

Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval

The task of hot-refresh model upgrades of image retrieval systems plays ...

Online Backfilling with No Regret for Large-Scale Image Retrieval

Backfilling is the process of re-extracting all gallery embeddings from ...

Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval

The task of privacy-preserving model upgrades in image retrieval desires...

Backward-Compatible Prediction Updates: A Probabilistic Approach

When machine learning systems meet real world applications, accuracy is ...

Learning Compatible Embeddings

Achieving backward compatibility when rolling out new models can highly ...

L^2R: Lifelong Learning for First-stage Retrieval with Backward-Compatible Representations

First-stage retrieval is a critical task that aims to retrieve relevant ...

Please sign up or login with your details

Forgot password? Click here to reset