LibMTL.weighting.Aligned_MTL

class Aligned_MTL[source]

Bases: LibMTL.weighting.abstract_weighting.AbsWeighting

Aligned-MTL.

This method is proposed in Independent Component Alignment for Multi-Task Learning (CVPR 2023) and implemented by modifying from the official PyTorch implementation.

backward(self, losses, **kwargs)[source]
Parameters

  • losses (list) – A list of losses of each task.

  • kwargs (dict) – A dictionary of hyperparameters of weighting methods.