# Visualizing Deep Similarity Networks

arXiv: https://arxiv.org/abs/1901.00536 · HTML: https://mlsanity.com/paper/1901.00536/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2019.

## Built on by (most cited first, 24 of 24)

- [Biometrics: Trust, but Verify](https://mlsanity.com/paper/2105.06625/) (2021)
- [Visual correspondence-based explanations improve AI robustness and human-AI team accuracy](https://mlsanity.com/paper/2208.00780/) (2022)
- [Explainable Person Re-Identification with Attribute-guided Metric Distillation](https://mlsanity.com/paper/2103.01451/) (2021)
- [DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification](https://mlsanity.com/paper/2112.04016/) (2021)
- [Conditional Identity Disentanglement for Differential Face Morph Detection](https://mlsanity.com/paper/2107.02162/) (2021)
- [Attributable Visual Similarity Learning](https://mlsanity.com/paper/2203.14932/) (2022)
- [Towards Visual Saliency Explanations of Face Verification](https://mlsanity.com/paper/2305.08546/) (2023)
- [GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps](https://mlsanity.com/paper/2109.00951/) (2021)
- [VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptation](https://mlsanity.com/paper/2202.10301/) (2022)
- [Visualizing and Understanding Contrastive Learning](https://mlsanity.com/paper/2206.09753/) (2022)
- [3D Face Reconstruction: the Road to Forensics](https://mlsanity.com/paper/2309.11357/) (2023)
- [Do Different Deep Metric Learning Losses Lead to Similar Learned Features?](https://mlsanity.com/paper/2205.02698/) (2022)
- [Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2307.03240/) (2023)
- [Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers](https://mlsanity.com/paper/2311.02803/) (2023)
- [Discriminative Deep Feature Visualization for Explainable Face Recognition](https://mlsanity.com/paper/2306.00402/) (2023)
- [Parallel Backpropagation for Shared-Feature Visualization](https://mlsanity.com/paper/2405.09827/) (2024)
- [Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution](https://mlsanity.com/paper/2202.03126/) (2022)
- [ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer](https://mlsanity.com/paper/2310.04099/) (2023)
- [Generalizing GradCAM for Embedding Networks](https://mlsanity.com/paper/2402.00909/) (2024)
- [Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary](https://mlsanity.com/paper/2304.06249/) (2023)
- [Towards A Comprehensive Visual Saliency Explanation Framework for AI-based Face Recognition Systems](https://mlsanity.com/paper/2407.05983/) (2024)
- [Improving Few-shot Learning with Weakly-supervised Object Localization](https://mlsanity.com/paper/2105.11715/) (2021)
- [Attention-based Dynamic Subspace Learners for Medical Image Analysis](https://mlsanity.com/paper/2206.09068/) (2022)
- [Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal Data](https://mlsanity.com/paper/2305.00320/) (2023)

## Abstract (arXiv)

For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for classification networks, but applicable to the problem domains better suited to similarity learning. The visualization shows how similarity networks that are fine-tuned learn to focus on different features. We also generalize our approach to embedding networks that use different pooling strategies and provide a simple mechanism to support image similarity searches on objects or sub-regions in the query image.