# Local Similarity-Aware Deep Feature Embedding

arXiv: https://arxiv.org/abs/1610.08904 · HTML: https://mlsanity.com/paper/1610.08904/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2016.

## Built on by (most cited first, 15 of 15)

- [Deep Relational Metric Learning](https://mlsanity.com/paper/2108.10026/) (2021)
- [Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks](https://mlsanity.com/paper/2311.01038/) (2023)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Contrastive Bayesian Analysis for Deep Metric Learning](https://mlsanity.com/paper/2210.04402/) (2022)
- [LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization](https://mlsanity.com/paper/2410.17020/) (2024)
- [LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning](https://mlsanity.com/paper/2108.09335/) (2021)
- [BITES: Balanced Individual Treatment Effect for Survival data](https://mlsanity.com/paper/2201.03448/) (2022)
- [Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimation](https://mlsanity.com/paper/2407.01111/) (2024)
- [GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning](https://mlsanity.com/paper/2410.15266/) (2024)
- [Neural Bregman Divergences for Distance Learning](https://mlsanity.com/paper/2206.04763/) (2022)
- [Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval](https://mlsanity.com/paper/2403.00272/) (2024)
- [Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud Classification](https://mlsanity.com/paper/2201.11388/) (2022)
- [Cascading Hierarchical Networks with Multi-task Balanced Loss for Fine-grained hashing](https://mlsanity.com/paper/2303.11274/) (2023)
- [DAAL: Density-Aware Adaptive Line Margin Loss for Multi-Modal Deep Metric Learning](https://mlsanity.com/paper/2410.05438/) (2024)
- [Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices](https://mlsanity.com/paper/2508.01580/) (2025)

## Abstract (arXiv)

Existing deep embedding methods in vision tasks are capable of learning a compact Euclidean space from images, where Euclidean distances correspond to a similarity metric. To make learning more effective and efficient, hard sample mining is usually employed, with samples identified through computing the Euclidean feature distance. However, the global Euclidean distance cannot faithfully characterize the true feature similarity in a complex visual feature space, where the intraclass distance in a high-density region may be larger than the interclass distance in low-density regions. In this paper, we introduce a Position-Dependent Deep Metric (PDDM) unit, which is capable of learning a similarity metric adaptive to local feature structure. The metric can be used to select genuinely hard samples in a local neighborhood to guide the deep embedding learning in an online and robust manner. The new layer is appealing in that it is pluggable to any convolutional networks and is trained end-to-end. Our local similarity-aware feature embedding not only demonstrates faster convergence and boosted performance on two complex image retrieval datasets, its large margin nature also leads to superior generalization results under the large and open set scenarios of transfer learning and zero-shot learning on ImageNet 2010 and ImageNet-10K datasets.