</> Code with Papers by Syntology

Methods › General › Twin Networks › Siamese Network

Siamese Network

introduced 1993 343 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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 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.

Intuitively 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.

Source: Koch et al

Papers archive 2025-07-28

30 shown of 343, 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.

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.

TaskPapers
Object39
Object Tracking32
Representation Learning24
Retrieval24
Triplet24
Contrastive Learning21
Change Detection19
Self-Supervised Learning19
Visual Tracking17
Object Detection16
Visual Object Tracking16
object-detection16
Classification15
Metric Learning14
Semantic Segmentation14
General Classification13
Transfer Learning13
Sentence12
Data Augmentation11
Decoder11

Usage over time archive 2025-07-28

Papers per year tagged with Siamese Network: 2014 to 2025, peak 61 61 0 2014: 1 paper 2014 2015: 4 papers 2015 2016: 3 papers 2016 2017: 13 papers 2017 2018: 26 papers 2018 2019: 42 papers 2019 2020: 61 papers 2020 2021: 55 papers 2021 2022: 49 papers 2022 2023: 46 papers 2023 2024: 32 papers 2024 2025: 11 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (343 dated). Bars are counts, not a trend claim.

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

Twin Networks

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