InfoNCE variants demonstrate direct and indirect coupling between the alignment and uniformity terms thus hurting optimisation. The Decoupled Hyperspherical Energy Loss (DHEL) is an NT-Xent variant that completly decouples alignment from uniformity by discarding the corresponding terms from the denominator. In this way optimisation is more efficient and robust to hyper parameter changes.

A method that randomly mask out all features coming from a specific time-step in time-series data. If the model used is independent of uneven sequences or missing data in time-series, like attention-based transformers, the masked time-steps can be just ignored in the forward prediction of the model. Otherwise, they have to be masked out with some numerical value.

Temporal Dropout

Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations

DHEL

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses

CRTracker is an end-to-end cross-view referring multi-object tracking method.

Source	Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
Year
Data Source	Papers with Code archive (CC BY-SA)