NTXent, or Normalized Temperaturescaled Cross Entropy Loss, is a loss function. Let $\text{sim}\left(\mathbf{u}, \mathbf{v}\right) = \mathbf{u}^{T}\mathbf{v}/\mathbf{u} \mathbf{v}$ denote the cosine similarity between two vectors $\mathbf{u}$ and $\mathbf{v}$. Then the loss function for a positive pair of examples $\left(i, j\right)$ is :
$$ \mathbb{l}_{i,j} = \log\frac{\exp\left(\text{sim}\left(\mathbf{z}_{i}, \mathbf{z}_{j}\right)/\tau\right)}{\sum^{2N}_{k=1}\mathcal{1}_{[k\neq{i}]}\exp\left(\text{sim}\left(\mathbf{z}_{i}, \mathbf{z}_{k}\right)/\tau\right)}$$
where $\mathcal{1}_{[k\neq{i}]} \in ${$0, 1$} is an indicator function evaluating to $1$ iff $k\neq{i}$ and $\tau$ denotes a temperature parameter. The final loss is computed across all positive pairs, both $\left(i, j\right)$ and $\left(j, i\right)$, in a minibatch.
Source: SimCLR
Source: Improved Deep Metric Learning with Multiclass Npair Loss ObjectivePaper  Code  Results  Date  Stars 

Task  Papers  Share 

SelfSupervised Learning  47  27.81% 
Image Classification  10  5.92% 
General Classification  8  4.73% 
Object Detection  5  2.96% 
SelfSupervised Image Classification  4  2.37% 
Image Retrieval  4  2.37% 
SemiSupervised Image Classification  4  2.37% 
Metric Learning  3  1.78% 
Time Series  2  1.18% 
Component  Type 


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