InfoNCE, where NCE stands for NoiseContrastive Estimation, is a type of contrastive loss function used for selfsupervised learning.
Given a set $X = ${$x_{1}, \dots, x_{N}$} of $N$ random samples containing one positive sample from $p\left(x_{t+k}c_{t}\right)$ and $N − 1$ negative samples from the 'proposal' distribution $p\left(x_{t+k}\right)$, we optimize:
$$ \mathcal{L}_{N} =  \mathbb{E}_{X}\left[\log\frac{f_{k}\left(x_{t+k}, c_{t}\right)}{\sum_{x_{j}\in{X}}f_{k}\left(x_{j}, c_{t}\right)}\right] $$
Optimizing this loss will result in $f_{k}\left(x_{t+k}, c_{t}\right)$ estimating the density ratio, which is:
$$ f_{k}\left(x_{t+k}, c_{t}\right) \propto \frac{p\left(x_{t+k}c_{t}\right)}{p\left(x_{t+k}\right)} $$
Source: Representation Learning with Contrastive Predictive CodingPaper  Code  Results  Date  Stars 

Task  Papers  Share 

SelfSupervised Learning  91  15.19% 
Image Classification  22  3.67% 
Retrieval  19  3.17% 
Semantic Segmentation  15  2.50% 
Object Detection  14  2.34% 
SelfSupervised Image Classification  14  2.34% 
General Classification  11  1.84% 
Speech Recognition  10  1.67% 
Language Modelling  10  1.67% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 