Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer

TL;DR

This paper introduces an orthogonal transformation layer that expands feature space and aligns new visual representations with old ones, enabling backward compatibility without re-indexing and improving accuracy.

Contribution

The paper proposes a novel orthogonal transformation approach that maintains backward compatibility while integrating new information, outperforming existing methods.

Findings

Maintains compatibility with previous models on CIFAR-100 and ImageNet-1k.

Eliminates the need for re-indexing during model updates.

Achieves state-of-the-art accuracy in visual retrieval tasks.

Abstract

Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new representations. The costly and resource-intensive backfilling process involves recalculating feature vectors for images in the gallery set whenever a new model is introduced. To address this, prior research has explored backward-compatible training methods that enable direct comparisons between new and old representations without backfilling. Despite these advancements, achieving a balance between backward compatibility and the performance of independently trained models remains an open problem. In this paper, we address it by expanding the representation space with additional dimensions and learning an orthogonal transformation to achieve compatibility with old models and, at the same time, integrate new information. This transformation preserves the original feature space's geometry, ensuring that our model aligns with previous versions while also learning new data. Our Orthogonal Compatible Aligned (OCA) approach eliminates the need for re-indexing during model updates and ensures that features can be compared directly across different model updates without additional mapping functions. Experimental results on CIFAR-100 and ImageNet-1k demonstrate that our method not only maintains compatibility with previous models but also achieves state-of-the-art accuracy, outperforming several existing methods.