Methods › General › Loss Functions › Supervised Contrastive Loss

Supervised Contrastive Loss

76 papers tagged archive 2025-07-28

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

Supervised Contrastive Loss is an alternative loss function to cross entropy that the authors argue can leverage label information more effectively. Clusters of points belonging to the same class are pulled together in embedding space, while simultaneously pushing apart clusters of samples from different classes.

ℒˢᵘᵖ=∑ᵢ₌₁²ᴺℒᵢˢᵘᵖ

ℒᵢˢᵘᵖ=(-1)/(2N_(ỹᵢ)-1)∑ⱼ₌₁²ᴺ1_(i≠j)·1_(ỹᵢ=ỹⱼ)·log(exp(zᵢ·zⱼ/τ))/(∑ₖ₌₁²ᴺ1_(i≠k)·exp(zᵢ·zₖ/τ))

where N_(ỹᵢ) is the total number of images in the minibatch that have the same label, ỹᵢ, as the anchor, i. This loss has important properties well suited for supervised learning: (a) generalization to an arbitrary number of positives, (b) contrastive power increases with more negatives.

Source: Supervised Contrastive LearningSee Code · HobbitLong/SupContrast

Papers archive 2025-07-28

30 shown of 76, 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 132 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
Contrastive Learning49
Representation Learning22
Image Classification11
Classification5
Long-tail Learning5
Self-Supervised Learning5
image-classification5
Data Augmentation4
Semantic Segmentation4
Time Series4
Attribute3
Class Incremental Learning3
Continual Learning3
Diagnostic3
Domain Generalization3
Face Swapping3
Knowledge Distillation3
Transfer Learning3
Change Detection2
Decoder2

Usage over time archive 2025-07-28

Papers per year tagged with Supervised Contrastive Loss: 2020 to 2025, peak 21 21 0 2020: 2 papers 2020 2021: 21 papers 2021 2022: 16 papers 2022 2023: 18 papers 2023 2024: 15 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (76 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

Loss Functions

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