Towards Backward-compatible Representation Learning

Abstract

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 succe

Stats

• citations52
• S2 citations—
• github stars0
• HF likes0
• heat score12.93
• arxiv keyshen2020towards

Related papers

• Forward Compatible Training For Large-scale Embedding Retrieval Systems (2021)8.09
• Learning Compatible Embeddings (2021)13.80
• Boundary-aware Backward-compatible Representation Via Adversarial Learning In Image Retrieval (2023)9.21
• Backward-compatible Aligned Representations Via An Orthogonal Transformation Layer (2024)0.00
• Unified Representation Learning For Cross Model Compatibility (2020)5.24
• Privacy-preserving Model Upgrades With Bidirectional Compatible Training In Image Retrieval (2022)0.00
• Towards Cross-modal Backward-compatible Representation Learning For Vision-language Models (2024)0.00
• Metric Compatible Training For Online Backfilling In Large-scale Retrieval (2023)2.26