Metric Compatible Training For Online Backfilling In Large-scale Retrieval

Abstract

Backfilling is the process of re-extracting all gallery embeddings from upgraded models in image retrieval systems. It inevitably requires a prohibitively large amount of computational cost and even entails the downtime of the service. Although backward-compatible learning sidesteps this challenge by tackling query-side representations, this leads to suboptimal solutions in principle because gallery embeddings cannot benefit from model upgrades. We address this dilemma by introducing an online backfilling algorithm, which enables us to achieve a progressive performance improvement during the backfilling process while not sacrificing the final performance of new model after the completion of backfilling. To this end, we first propose a simple distance rank merge technique for online backfilling. Then, we incorporate a reverse transformation module for more effective and efficient merging, which is further enhanced by adopting a metric-compatible contrastive learning approach. These two

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyseo2023metric

Related papers

• Privacy-preserving Model Upgrades With Bidirectional Compatible Training In Image Retrieval (2022)0.00
• Forward Compatible Training For Large-scale Embedding Retrieval Systems (2021)8.09
• Fastfill: Efficient Compatible Model Update (2023)0.00
• Boundary-aware Backward-compatible Representation Via Adversarial Learning In Image Retrieval (2023)9.21
• Towards Backward-compatible Representation Learning (2020)12.93
• Hot-refresh Model Upgrades With Regression-alleviating Compatible Training In Image Retrieval (2022)2.83
• Backward-compatible Aligned Representations Via An Orthogonal Transformation Layer (2024)0.00
• Learning Compatible Embeddings (2021)13.80