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

04/29/2022
by   Shupeng Su, et al.
5

The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images. A pioneering work introduced backward-compatible training, where the new model can be directly deployed in a backfill-free manner, i.e., the new query can be directly compared to the old gallery features. Despite a possible solution, its improvement in sequential model upgrades is gradually limited by the fixed and under-quality old gallery embeddings. To this end, we propose a new model upgrade paradigm, termed Bidirectional Compatible Training (BiCT), which will upgrade the old gallery embeddings by forward-compatible training towards the embedding space of the backward-compatible new model. We conduct comprehensive experiments to verify the prominent improvement by BiCT and interestingly observe that the inconspicuous loss weight of backward compatibility actually plays an essential role for both backward and forward retrieval performance. To summarize, we introduce a new and valuable problem named privacy-preserving model upgrades, with a proper solution BiCT. Several intriguing insights are further proposed to get the most out of our method.

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
05/04/2023

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

Image retrieval plays an important role in the Internet world. Usually, ...
research
08/07/2021

Neighborhood Consensus Contrastive Learning for Backward-Compatible Representation

In object re-identification (ReID), the development of deep learning tec...
research
01/10/2023

Online Backfilling with No Regret for Large-Scale Image Retrieval

Backfilling is the process of re-extracting all gallery embeddings from ...
research
01/24/2022

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

The task of hot-refresh model upgrades of image retrieval systems plays ...
research
11/08/2022

BT^2: Backward-compatible Training with Basis Transformation

Modern retrieval system often requires recomputing the representation of...
research
07/12/2022

Dynamic Gradient Reactivation for Backward Compatible Person Re-identification

We study the backward compatible problem for person re-identification (R...

Please sign up or login with your details

Forgot password? Click here to reset