{"url":"/method/triplet-loss","slug":"triplet-loss","name":"Triplet Loss","full_name":"Triplet Loss","full_name_withheld":false,"description_markdown":"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:\r\n\r\n$$\r\nL\\_{t}\\left(\\mathcal{V}\\_{p}, \\mathcal{V}\\_{n}\\right)=-\\frac{1}{M N} \\sum\\_{i}^{M} \\sum\\_{j}^{N} \\log \\operatorname{prob}\\left(v p\\_{i}, v n\\_{j}\\right)\r\n$$\r\n\r\nwhere the balance weight $1/MN$ is used to keep the loss with the same scale for different number of instance sets.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Triplet Loss in Siamese Network for Object Tracking","paper":"/paper/triplet-loss-in-siamese-network-for-object","first_author":"Xingping Dong","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/triplet-loss-in-siamese-network-for-object"},"source":{"url":"http://openaccess.thecvf.com/content_ECCV_2018/html/Xingping_Dong_Triplet_Loss_with_ECCV_2018_paper.html","title":"Triplet Loss in Siamese Network for Object Tracking","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":424,"archive_num_papers":424,"papers_newest_first":[{"paper":null,"title":"Self-supervised Feature Extraction for Enhanced Ball Detection on Soccer Robots","date":"2025-06-20","arxiv_id":"2506.16821","n_code_links":0,"syntology":null},{"paper":null,"title":"Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories","date":"2025-06-03","arxiv_id":"2506.02571","n_code_links":0,"syntology":null},{"paper":null,"title":"Exploring Generalized Gait Recognition: Reducing Redundancy and Noise within Indoor and Outdoor Datasets","date":"2025-05-21","arxiv_id":"2505.15176","n_code_links":0,"syntology":null},{"paper":"/paper/deeclip-a-robust-and-generalizable","title":"DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images","date":"2025-04-28","arxiv_id":"2504.19876","n_code_links":1,"syntology":null},{"paper":"/paper/contrastivegaussian-high-fidelity-3d","title":"ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting","date":"2025-04-10","arxiv_id":"2504.08100","n_code_links":1,"syntology":null},{"paper":"/paper/multi-task-learning-with-multi-annotation","title":"Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection","date":"2025-04-10","arxiv_id":"2504.08054","n_code_links":1,"syntology":null},{"paper":"/paper/tune-it-up-music-genre-transfer-and","title":"Tune It Up: Music Genre Transfer and Prediction","date":"2025-03-27","arxiv_id":"2503.22008","n_code_links":1,"syntology":null},{"paper":null,"title":"CoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation","date":"2025-03-25","arxiv_id":"2503.19661","n_code_links":0,"syntology":null},{"paper":null,"title":"Edgeworth Expansion for Semi-hard Triplet Loss","date":"2025-03-17","arxiv_id":"2503.12893","n_code_links":0,"syntology":null},{"paper":null,"title":"Radar Pulse Deinterleaving with Transformer Based Deep Metric Learning","date":"2025-03-04","arxiv_id":"2503.13476","n_code_links":0,"syntology":null},{"paper":null,"title":"GenIAS: Generator for Instantiating Anomalies in time Series","date":"2025-02-12","arxiv_id":"2502.08262","n_code_links":0,"syntology":null},{"paper":null,"title":"PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL","date":"2025-02-07","arxiv_id":"2502.05237","n_code_links":0,"syntology":null},{"paper":null,"title":"Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning","date":"2025-01-16","arxiv_id":"2501.09608","n_code_links":0,"syntology":null},{"paper":null,"title":"FARE: A Deep Learning-Based Framework for Radar-based Face Recognition and Out-of-distribution Detection","date":"2025-01-14","arxiv_id":"2501.08440","n_code_links":0,"syntology":null},{"paper":null,"title":"Anomaly Triplet-Net: Progress Recognition Model Using Deep Metric Learning Considering Occlusion for Manual Assembly Work","date":"2025-01-07","arxiv_id":"2501.03533","n_code_links":0,"syntology":null},{"paper":"/paper/siamese-networks-for-cat-re-identification","title":"Siamese Networks for Cat Re-Identification: Exploring Neural Models for Cat Instance Recognition","date":"2025-01-03","arxiv_id":"2501.02112","n_code_links":1,"syntology":null},{"paper":null,"title":"Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification","date":"2024-12-28","arxiv_id":"2412.20110","n_code_links":0,"syntology":null},{"paper":null,"title":"Hyperbolic-constraint Point Cloud Reconstruction from Single RGB-D Images","date":"2024-12-12","arxiv_id":"2412.09055","n_code_links":0,"syntology":null},{"paper":null,"title":"Securing Social Media Against Deepfakes using Identity, Behavioral, and Geometric Signatures","date":"2024-12-07","arxiv_id":"2412.05487","n_code_links":0,"syntology":null},{"paper":null,"title":"Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification","date":"2024-11-28","arxiv_id":"2411.19215","n_code_links":0,"syntology":null},{"paper":null,"title":"Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval","date":"2024-11-22","arxiv_id":"2411.14704","n_code_links":0,"syntology":null},{"paper":null,"title":"Leveraging large language models for efficient representation learning for entity resolution","date":"2024-11-15","arxiv_id":"2411.10629","n_code_links":0,"syntology":null},{"paper":null,"title":"Marker-free Human Gait Analysis using a Smart Edge Sensor System","date":"2024-11-14","arxiv_id":"2411.09538","n_code_links":0,"syntology":null},{"paper":"/paper/trig-ner-triplet-grid-framework-for","title":"TriG-NER: Triplet-Grid Framework for Discontinuous Named Entity Recognition","date":"2024-11-04","arxiv_id":"2411.01839","n_code_links":1,"syntology":null},{"paper":null,"title":"Prototypical Extreme Multi-label Classification with a Dynamic Margin Loss","date":"2024-10-27","arxiv_id":"2410.20401","n_code_links":0,"syntology":null},{"paper":null,"title":"GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting","date":"2024-10-22","arxiv_id":"2410.16647","n_code_links":0,"syntology":null},{"paper":null,"title":"Contrastive Learning for Character Detection in Ancient Greek Papyri","date":"2024-09-16","arxiv_id":"2409.10156","n_code_links":0,"syntology":null},{"paper":null,"title":"Use of triplet loss for facial restoration in low-resolution images","date":"2024-09-05","arxiv_id":"2409.03530","n_code_links":0,"syntology":null},{"paper":null,"title":"Pureformer-VC: Non-parallel One-Shot Voice Conversion with Pure Transformer Blocks and Triplet Discriminative Training","date":"2024-09-03","arxiv_id":"2409.01668","n_code_links":0,"syntology":null},{"paper":null,"title":"Breast tumor classification based on self-supervised contrastive learning from ultrasound videos","date":"2024-08-20","arxiv_id":"2408.10600","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":null,"name":"Triplet","papers":410},{"task":"/task/retrieval","name":"Retrieval","papers":82},{"task":"/task/metric-learning","name":"Metric Learning","papers":80},{"task":"/task/person-re-identification","name":"Person Re-Identification","papers":46},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":35},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":32},{"task":"/task/representation-learning","name":"Representation Learning","papers":32},{"task":"/task/face-recognition","name":"Face Recognition","papers":22},{"task":"/task/classification","name":"General Classification","papers":21},{"task":"/task/image-classification","name":"Image Classification","papers":20},{"task":"/task/image-classification","name":"image-classification","papers":20},{"task":"/task/clustering","name":"Clustering","papers":19},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":17},{"task":"/task/classification-1","name":"Classification","papers":16},{"task":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval","papers":16},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":15},{"task":"/task/sentence","name":"Sentence","papers":15},{"task":"/task/object-detection","name":"Object Detection","papers":14},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":14},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":13}],"tasks_shown":20,"n_tasks":358,"usage_by_year":[{"year":"2018","papers":16},{"year":"2019","papers":68},{"year":"2020","papers":76},{"year":"2021","papers":83},{"year":"2022","papers":60},{"year":"2023","papers":60},{"year":"2024","papers":45},{"year":"2025","papers":16}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/triplet-loss"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}