BLENDER: Blended Text Embeddings and Diffusion Residuals for Intra-Class Image Synthesis in Deep Metric Learning

TL;DR

BLENDeR introduces a diffusion-based method that uses set-theory inspired operations to generate diverse, controllable synthetic data for deep metric learning, improving intra-class diversity and model performance.

Contribution

The paper presents BLenDeR, a novel diffusion sampling technique employing union and intersection operations on residuals to enhance intra-class diversity in DML.

Findings

Outperforms state-of-the-art baselines on multiple datasets.

Achieves 3.7% increase in Recall@1 on CUB-200.

Achieves 1.8% increase in Recall@1 on Cars-196.

Abstract

The rise of Deep Generative Models (DGM) has enabled the generation of high-quality synthetic data. When used to augment authentic data in Deep Metric Learning (DML), these synthetic samples enhance intra-class diversity and improve the performance of downstream DML tasks. We introduce BLenDeR, a diffusion sampling method designed to increase intra-class diversity for DML in a controllable way by leveraging set-theory inspired union and intersection operations on denoising residuals. The union operation encourages any attribute present across multiple prompts, while the intersection extracts the common direction through a principal component surrogate. These operations enable controlled synthesis of diverse attribute combinations within each class, addressing key limitations of existing generative approaches. Experiments on standard DML benchmarks demonstrate that BLenDeR consistently outperforms state-of-the-art baselines across multiple datasets and backbones. Specifically, BLenDeR achieves 3.7% increase in Recall@1 on CUB-200 and a 1.8% increase on Cars-196, compared to state-of-the-art baselines under standard experimental settings.