通過正交轉換層實現向後兼容的對齊表示

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer

August 16, 2024

作者: Simone Ricci, Niccolò Biondi, Federico Pernici, Alberto Del Bimbo

cs.AI

摘要

視覺檢索系統在更新具有改進表示的模型時面臨重大挑戰，原因是舊表示和新表示之間存在不一致。昂貴且資源密集的回填過程涉及當引入新模型時重新計算圖庫集中圖像的特徵向量。為了應對這一問題，先前的研究探索了向後兼容的訓練方法，使新舊表示之間可以直接進行比較，而無需回填。儘管取得了進展，但在向後兼容性和獨立訓練模型性能之間取得平衡仍然是一個未解決的問題。本文通過擴展表示空間的附加維度並學習正交轉換來實現與舊模型的兼容性，同時整合新信息來解決這一問題。這種轉換保留了原始特徵空間的幾何形狀，確保我們的模型與先前版本保持一致，同時學習新數據。我們的正交兼容對齊（OCA）方法消除了在模型更新期間重新索引的需要，確保特徵可以在不同模型更新之間直接進行比較，而無需額外的映射函數。在CIFAR-100和ImageNet-1k上的實驗結果表明，我們的方法不僅保持了與先前模型的兼容性，還實現了最先進的準確性，優於幾種現有方法。

English

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.