mlsanityData to 7 Oct 2026

Visualizing Deep Similarity Networks

arXiv 1901.00536 ↗First posted 2 Jan 2019cs.CV cs.LGcited by 24

Not on the map. Why?

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.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 7; 2023: 8; 2024: 3.

24 papers.

Sort:

  1. 2021Biometrics: Trust, but Verifycited by 39
  2. 2022Visual correspondence-based explanations improve AI robustness and human-AI team accuracycited by 37
  3. 2021Explainable Person Re-Identification with Attribute-guided Metric Distillationcited by 23
  4. 2021DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identificationcited by 20
  5. 2021Conditional Identity Disentanglement for Differential Face Morph Detectioncited by 12
  6. 2022Attributable Visual Similarity Learningcited by 12
  7. 2023Towards Visual Saliency Explanations of Face Verificationcited by 11
  8. 2021GAM: Explainable Visual Similarity and Classification via Gradient Activation Mapscited by 8
  9. 2022VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptationcited by 7
  10. 2022Visualizing and Understanding Contrastive Learningcited by 7
  11. 20233D Face Reconstruction: the Road to Forensicscited by 7
  12. 2022Do Different Deep Metric Learning Losses Lead to Similar Learned Features?cited by 6
12 more
  1. 2023Adaptive Generation of Privileged Intermediate Information for Visible-Infrared Person Re-Identificationcited by 6
  2. 2023Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformerscited by 4
  3. 2023Discriminative Deep Feature Visualization for Explainable Face Recognitioncited by 3
  4. 2024Parallel Backpropagation for Shared-Feature Visualizationcited by 3
  5. 2022Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attributioncited by 2
  6. 2023ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformercited by 2
  7. 2024Generalizing GradCAM for Embedding Networkscited by 2
  8. 2023Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabularycited by 1
  9. 2024Towards A Comprehensive Visual Saliency Explanation Framework for AI-based Face Recognition Systemscited by 1
  10. 2021Improving Few-shot Learning with Weakly-supervised Object Localizationcited by 0
  11. 2022Attention-based Dynamic Subspace Learners for Medical Image Analysiscited by 0
  12. 2023Fusion for Visual-Infrared Person ReID in Real-World Surveillance Using Corrupted Multimodal Datacited by 0