{"url":"/method/siamese-network","slug":"siamese-network","name":"Siamese Network","full_name":"Siamese Network","full_name_withheld":false,"description_markdown":"A **Siamese Network** consists of twin networks which accept distinct inputs but are joined by an energy function at the top. This function computes a metric between the highest level feature representation on each side. The parameters between the twin networks are tied. [Weight tying](https://paperswithcode.com/method/weight-tying) guarantees that two extremely similar images are not mapped by each network to very different locations in feature space because each network computes the same function. The network is symmetric, so that whenever we present two distinct images to the twin networks, the top conjoining layer will compute the same metric as if we were to we present the same two images but to the opposite twins.\r\n\r\nIntuitively instead of trying to classify inputs, a siamese network learns to differentiate between inputs, learning their similarity. The loss function used is usually a form of contrastive loss.\r\n\r\nSource: [Koch et al](https://www.cs.cmu.edu/~rsalakhu/papers/oneshot1.pdf)","description_state":"present","introduced_year":1993,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Twin Networks","url":"/methods/category/twin-networks","pwc_aliases":[]}],"n_papers_tagged":343,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"title":"Dc-EEMF: Pushing depth-of-field limit of photoacoustic microscopy via decision-level constrained learning","date":"2025-05-29","arxiv_id":"2506.03181","n_code_links":0,"syntology":null},{"paper":null,"title":"GRAML: Goal Recognition As Metric Learning","date":"2025-05-06","arxiv_id":"2505.03941","n_code_links":0,"syntology":null},{"paper":null,"title":"FGSGT: Saliency-Guided Siamese Network Tracker Based on Key Fine-Grained Feature Information for Thermal Infrared Target Tracking","date":"2025-04-19","arxiv_id":"2504.14309","n_code_links":0,"syntology":null},{"paper":null,"title":"CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Models","date":"2025-04-07","arxiv_id":"2504.10498","n_code_links":0,"syntology":null},{"paper":null,"title":"A Siamese Network to Detect If Two Iris Images Are Monozygotic","date":"2025-03-12","arxiv_id":"2503.09749","n_code_links":0,"syntology":null},{"paper":null,"title":"Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains","date":"2025-02-13","arxiv_id":"2502.09089","n_code_links":0,"syntology":null},{"paper":null,"title":"TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer","date":"2025-02-05","arxiv_id":"2502.03426","n_code_links":0,"syntology":null},{"paper":null,"title":"An Analysis of LLM Fine-Tuning and Few-Shot Learning for Flaky Test Detection and Classification","date":"2025-02-04","arxiv_id":"2502.02715","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-detection-and-prediction-of-namd","title":"Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality","date":"2025-01-24","arxiv_id":"2501.14323","n_code_links":1,"syntology":null},{"paper":null,"title":"Embedding Similarity Guided License Plate Super Resolution","date":"2025-01-02","arxiv_id":"2501.01483","n_code_links":0,"syntology":null},{"paper":"/paper/deep-change-monitoring-a-hyperbolic","title":"Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detection","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"2by2: Weakly-Supervised Learning for Global Action Segmentation","date":"2024-12-17","arxiv_id":"2412.12829","n_code_links":0,"syntology":null},{"paper":"/paper/speech-separation-with-pretrained-frontend-to","title":"Speech Separation with Pretrained Frontend to Minimize Domain Mismatch","date":"2024-11-05","arxiv_id":"2411.03085","n_code_links":1,"syntology":null},{"paper":null,"title":"Detect an Object At Once without Fine-tuning","date":"2024-11-04","arxiv_id":"2411.02181","n_code_links":0,"syntology":null},{"paper":null,"title":"Using Deep Neural Networks to Quantify Parking Dwell Time","date":"2024-10-31","arxiv_id":"2411.00158","n_code_links":0,"syntology":null},{"paper":null,"title":"Development of Image Collection Method Using YOLO and Siamese Network","date":"2024-10-16","arxiv_id":"2410.12561","n_code_links":0,"syntology":null},{"paper":"/paper/frequency-temporal-attention-network-for-1","title":"Frequency-Temporal Attention Network for Remote Sensing Imagery Change Detection","date":"2024-10-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Towards the generation of hierarchical attack models from cybersecurity vulnerabilities using language models","date":"2024-10-07","arxiv_id":"2410.05351","n_code_links":0,"syntology":null},{"paper":null,"title":"Intelligent Repetition Counting for Unseen Exercises: A Few-Shot Learning Approach with Sensor Signals","date":"2024-10-01","arxiv_id":"2410.00407","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion","date":"2024-09-15","arxiv_id":"2409.09616","n_code_links":0,"syntology":null},{"paper":"/paper/change-aware-siamese-network-for-surface","title":"Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background","date":"2024-09-01","arxiv_id":"2409.00589","n_code_links":1,"syntology":null},{"paper":"/paper/crossfi-a-cross-domain-wi-fi-sensing","title":"CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network","date":"2024-08-20","arxiv_id":"2408.10919","n_code_links":1,"syntology":null},{"paper":null,"title":"Multi-turn Response Selection with Commonsense-enhanced Language Models","date":"2024-07-26","arxiv_id":"2407.18479","n_code_links":0,"syntology":null},{"paper":null,"title":"A Multi-view Mask Contrastive Learning Graph Convolutional Neural Network for Age Estimation","date":"2024-07-23","arxiv_id":"2407.16234","n_code_links":0,"syntology":null},{"paper":"/paper/multi-modal-masked-siamese-network-improves","title":"Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning","date":"2024-07-05","arxiv_id":"2407.04449","n_code_links":3,"syntology":null},{"paper":"/paper/siamtst-a-novel-representation-learning","title":"SiamTST: A Novel Representation Learning Framework for Enhanced Multivariate Time Series Forecasting applied to Telco Networks","date":"2024-07-02","arxiv_id":"2407.02258","n_code_links":1,"syntology":null},{"paper":null,"title":"ADSNet: Cross-Domain LTV Prediction with an Adaptive Siamese Network in Advertising","date":"2024-06-15","arxiv_id":"2406.10517","n_code_links":0,"syntology":null},{"paper":null,"title":"Asymmetrical Siamese Network for Point Clouds Normal Estimation","date":"2024-06-14","arxiv_id":"2406.09681","n_code_links":0,"syntology":null},{"paper":null,"title":"Towards AI Lesion Tracking in PET/CT Imaging: A Siamese-based CNN Pipeline applied on PSMA PET/CT Scans","date":"2024-06-13","arxiv_id":"2406.09327","n_code_links":0,"syntology":null},{"paper":"/paper/genomics-guided-representation-learning-for","title":"Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction","date":"2024-06-10","arxiv_id":"2406.06517","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/object","name":"Object","papers":39},{"task":"/task/object-tracking","name":"Object Tracking","papers":32},{"task":"/task/representation-learning","name":"Representation Learning","papers":24},{"task":"/task/retrieval","name":"Retrieval","papers":24},{"task":null,"name":"Triplet","papers":24},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":21},{"task":"/task/change-detection","name":"Change Detection","papers":19},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":19},{"task":"/task/visual-tracking","name":"Visual Tracking","papers":17},{"task":"/task/object-detection","name":"Object Detection","papers":16},{"task":"/task/visual-object-tracking","name":"Visual Object Tracking","papers":16},{"task":"/task/object-detection-1","name":"object-detection","papers":16},{"task":"/task/classification-1","name":"Classification","papers":15},{"task":"/task/metric-learning","name":"Metric Learning","papers":14},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":14},{"task":"/task/classification","name":"General Classification","papers":13},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":13},{"task":"/task/sentence","name":"Sentence","papers":12},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":11},{"task":"/task/decoder","name":"Decoder","papers":11}],"tasks_shown":20,"n_tasks":358,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":4},{"year":"2016","papers":3},{"year":"2017","papers":13},{"year":"2018","papers":26},{"year":"2019","papers":42},{"year":"2020","papers":61},{"year":"2021","papers":55},{"year":"2022","papers":49},{"year":"2023","papers":46},{"year":"2024","papers":32},{"year":"2025","papers":11}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/siamese-network"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}