Methods › General › Loss Functions › Triplet Loss
Triplet Loss
Introduced by Xingping Dong et al. in Triplet Loss in Siamese Network for Object Tracking
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its negative logarithm, we can get the loss formulation as follows:
Lₜ(𝒱ₚ, 𝒱ₙ)=-1/(M N) ∑ᵢᴹ ∑ⱼᴺ logprob(v pᵢ, v nⱼ)
where the balance weight 1/MN is used to keep the loss with the same scale for different number of instance sets.
Papers archive 2025-07-28
30 shown of 424, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots 20 Jun 2025 · 0 repositories · arXiv:2506.16821
-
Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories 3 Jun 2025 · 0 repositories · arXiv:2506.02571
-
Exploring Generalized Gait Recognition: Reducing Redundancy and Noise within Indoor and Outdoor Datasets 21 May 2025 · 0 repositories · arXiv:2505.15176
-
DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images 28 Apr 2025 · 1 repository · arXiv:2504.19876
-
ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting 10 Apr 2025 · 1 repository · arXiv:2504.08100
-
Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection 10 Apr 2025 · 1 repository · arXiv:2504.08054
-
Tune It Up: Music Genre Transfer and Prediction 27 Mar 2025 · 1 repository · arXiv:2503.22008
-
CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation 25 Mar 2025 · 0 repositories · arXiv:2503.19661
-
Edgeworth Expansion for Semi-hard Triplet Loss 17 Mar 2025 · 0 repositories · arXiv:2503.12893
-
Radar Pulse Deinterleaving with Transformer Based Deep Metric Learning 4 Mar 2025 · 0 repositories · arXiv:2503.13476
-
GenIAS: Generator for Instantiating Anomalies in time Series 12 Feb 2025 · 0 repositories · arXiv:2502.08262
-
PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL 7 Feb 2025 · 0 repositories · arXiv:2502.05237
-
Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning 16 Jan 2025 · 0 repositories · arXiv:2501.09608
-
FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection 14 Jan 2025 · 0 repositories · arXiv:2501.08440
-
Anomaly Triplet-Net: Progress Recognition Model Using Deep Metric Learning Considering Occlusion for Manual Assembly Work 7 Jan 2025 · 0 repositories · arXiv:2501.03533
-
Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance Recognition 3 Jan 2025 · 1 repository · arXiv:2501.02112
-
Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification 28 Dec 2024 · 0 repositories · arXiv:2412.20110
-
Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images 12 Dec 2024 · 0 repositories · arXiv:2412.09055
-
Securing Social Media Against Deepfakes using Identity, Behavioral, and Geometric Signatures 7 Dec 2024 · 0 repositories · arXiv:2412.05487
-
Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification 28 Nov 2024 · 0 repositories · arXiv:2411.19215
-
Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval 22 Nov 2024 · 0 repositories · arXiv:2411.14704
-
Leveraging large language models for efficient representation learning for entity resolution 15 Nov 2024 · 0 repositories · arXiv:2411.10629
-
Marker-free Human Gait Analysis using a Smart Edge Sensor System 14 Nov 2024 · 0 repositories · arXiv:2411.09538
-
TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition 4 Nov 2024 · 1 repository · arXiv:2411.01839
-
Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss 27 Oct 2024 · 0 repositories · arXiv:2410.20401
-
GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting 22 Oct 2024 · 0 repositories · arXiv:2410.16647
-
Contrastive Learning for Character Detection in Ancient Greek Papyri 16 Sep 2024 · 0 repositories · arXiv:2409.10156
-
Use of triplet loss for facial restoration in low-resolution images 5 Sep 2024 · 0 repositories · arXiv:2409.03530
-
Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training 3 Sep 2024 · 0 repositories · arXiv:2409.01668
-
Breast tumor classification based on self-supervised contrastive learning from ultrasound videos 20 Aug 2024 · 0 repositories · arXiv:2408.10600
Tasks archive 2025-07-28
20 shown of 358 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections