Boundary-aware Backward-compatible Representation Via Adversarial Learning In Image Retrieval

Abstract

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 betwee

Stats

• citations10
• S2 citations—
• github stars4
• HF likes0
• heat score9.21
• arxiv keypan2023boundary

Related papers

• Privacy-preserving Model Upgrades With Bidirectional Compatible Training In Image Retrieval (2022)0.00
• Towards Backward-compatible Representation Learning (2020)12.93
• Metric Compatible Training For Online Backfilling In Large-scale Retrieval (2023)2.26
• Forward Compatible Training For Large-scale Embedding Retrieval Systems (2021)8.09
• Backward-compatible Aligned Representations Via An Orthogonal Transformation Layer (2024)0.00
• Towards Cross-modal Backward-compatible Representation Learning For Vision-language Models (2024)0.00
• Prototype Perturbation For Relaxing Alignment Constraints In Backward-compatible Learning (2025)0.00
• A Review Of Image Retrieval Techniques: Data Augmentation And Adversarial Learning Approaches (2024)0.00