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

arXiv: https://arxiv.org/abs/2601.20246 · HTML: https://mlsanity.com/paper/2601.20246/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 51 references that are in the map.
- First posted on arXiv 28 Jan 2026.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Sampling Matters in Deep Embedding Learning](https://mlsanity.com/paper/1706.07567/) (2017)
- [No Fuss Distance Metric Learning using Proxies](https://mlsanity.com/paper/1703.07464/) (2017)
- [Proxy Anchor Loss for Deep Metric Learning](https://mlsanity.com/paper/2003.13911/) (2020)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [Beyond triplet loss: a deep quadruplet network for person re-identification](https://mlsanity.com/paper/1704.01719/) (2017)
- [Hyperbolic Vision Transformers: Combining Improvements in Metric Learning](https://mlsanity.com/paper/2203.10833/) (2022)
- [ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis](https://mlsanity.com/paper/2004.01113/) (2020)
- [Revisiting Training Strategies and Generalization Performance in Deep Metric Learning](https://mlsanity.com/paper/2002.08473/) (2020)
- [Smart Mining for Deep Metric Learning](https://mlsanity.com/paper/1704.01285/) (2017)
- [The Principles of Diffusion Models](https://mlsanity.com/paper/2510.21890/) (2025)
- [IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models](https://mlsanity.com/paper/2308.04995/) (2023)
- [Improved Embeddings with Easy Positive Triplet Mining](https://mlsanity.com/paper/1904.04370/) (2019)
- [Hard-Aware Deeply Cascaded Embedding](https://mlsanity.com/paper/1611.05720/) (2016)

## Abstract (arXiv)

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.