mlsanityData to 7 Oct 2026

Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems

arXiv 2110.07933 ↗First posted 15 Oct 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are as close as possible. This issue becomes significantly heightened in complex computer vision tasks such as re-identification(reID). In this paper, we suggest that these dramatic appearance changes are indications that an object ID is composed of multiple natural groups, and it is counterproductive to forcefully map instances from different groups to a common location. This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature-matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID. We use this triplet mining mechanism to establish a pose-aware, well-conditioned triplet loss by implicitly enforcing view consistency. This allows a single network to be trained with fixed parameters across datasets while providing state-of-the-art results. Code is available at https://github.com/adhirajghosh/RPTM_reid.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

32 of 52 references.

References · 32

  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  3. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  4. 2019Relational Knowledge Distillationcited by 873
  5. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  6. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  7. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  8. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  9. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 119
  10. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  11. 2020Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrievalcited by 98
  12. 2020Hard negative examples are hard, but usefulcited by 82
20 more
  1. 2019Improved Embeddings with Easy Positive Triplet Miningcited by 66
  2. 2019Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identificationcited by 53
  3. 2020Parsing-based View-aware Embedding Network for Vehicle Re-Identificationcited by 53
  4. 2018Spatial-Temporal Person Re-identificationcited by 45
  5. 2019Vehicle Re-identification with Viewpoint-aware Metric Learningcited by 45
  6. 2020VehicleNet: Learning Robust Visual Representation for Vehicle Re-identificationcited by 42
  7. 2019MIC: Mining Interclass Characteristics for Improved Metric Learningcited by 41
  8. 2020The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identificationcited by 39
  9. 2019A Dual-Path Model With Adaptive Attention For Vehicle Re-Identificationcited by 34
  10. 2020PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Datacited by 31
  11. 2021Spatial-Temporal Correlation and Topology Learning for Person Re-Identification in Videoscited by 27
  12. 2020Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Networkcited by 26
  13. 2020Multi-Domain Learning and Identity Mining for Vehicle Re-Identificationcited by 18
  14. 2018Vehicle Re-identification Using Quadruple Directional Deep Learning Featurescited by 14
  15. 2020Top-DB-Net: Top DropBlock for Activation Enhancement in Person Re-Identificationcited by 14
  16. 2021Graph-based Person Signature for Person Re-Identificationscited by 14
  17. 2021A Strong Baseline for Vehicle Re-Identificationcited by 13
  18. 2019Attributes Guided Feature Learning for Vehicle Re-identificationcited by 12
  19. 2021SIFT Matching by Context Exposedcited by 9
  20. 2021AttributeNet: Attribute Enhanced Vehicle Re-Identificationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 2.

8 papers.

  1. 2024SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimapcited by 34
  2. 2023ViPE: Visualise Pretty-much Everythingcited by 3
  3. 2023Spatial-temporal Vehicle Re-identificationcited by 1
  4. 2025CORE-ReID: Comprehensive Optimization and Refinement through Ensemble fusion in Domain Adaptation for person re-identificationcited by 1
  5. 2024Study on Aspect Ratio Variability toward Robustness of Vision Transformer-based Vehicle Re-identificationcited by 0
  6. 2024Object Re-identification via Spatial-temporal Fusion Networks and Causal Identity Matchingcited by 0
  7. 2024TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognitioncited by 0
  8. 2025CLIPVehicle: A Unified Framework for Vision-based Vehicle Searchcited by 0