Forward Compatible Training for Large-Scale Embedding Retrieval Systems
By Vivek Ramanujan, Pavan Kumar Anasosalu Vasu, Ali Farhadi, Oncel Tuzel, Hadi Pouransari. 2021
25 citations recorded by the source corpus.
In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Re-cently, the idea of backward compatible training (BCT) was proposed. To avoid the cost of backfilling, BCT modifies training of the new model to make its representations com-patible with those of the old model. However, BCT can sig-nificantly hinder the performance of the new model. In this work, we propose a new learning paradigm for representation learning: forward compatible training (FCT). In Fct, when the old model is trained, we also prepare for a future unknown version of the model. We propose learning side- information, an auxiliary feature for each sample which fa-cilitates future updates of the model. To develop a powerful and flexible frameworkfor model compatibility, we combine side-information with a forward transformation from old to newembeddings. Training of the new model is not modified, hence, its accuracy is not degraded. We demonstrate sig-nificant retrieval accuracy improvement compared to BCT for various datasets: ImageNet-1k (+18.1%), Places-365 (+5.4%), and VGG-Face2 (+8.3%). Fctobtains model compatibility when the new and old models are trained across different datasets, losses, and architectures.11Code available at https://github.com/apple/ml-fct.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Learning Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification (2024, methodology): “Existing CT methods can be categorized into two branches: backward CT [16, 24, 39] and forward CT methods [21, 30, 45].”
- Metric Compatible Training for Online Backfilling in Large-Scale Retrieval (2023, unknown): “FCT [17] achieves meaningful performance improvement by transforming old gallery features, but most of the gains come from side-information [2].”
- Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval (2023, background): “Following this topic, compatible learning methods have developed into three branches: backward-compatible learning, forwardcompatible learning [15, 34], and cross-model compatible learning (CMC) [1,14,19,23].”
- Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models (2025, unknown): “The issue of non-compatibility has previously been studied in CL for image retrieval works (Ramanujan et al., 2022; Wan et al., 2022; Biondi et al., 2023).”