"downstream tasks" is a correct and usable phrase in written English.
It is typically used to refer to tasks that are dependent on or come after other tasks or steps in a process. For example, you could say, "Once the upstream tasks have been completed, we can begin working on the downstream tasks."
We propose evaluating word embeddings by using them as features in simple models for a suite of popular downstream tasks.
Why do we care about disentangling: What are the downstream tasks that can benefit from using disentangled representations?
This is analogous to word embeddings in NLP, where words are mapped to embeddings and used for various downstream tasks.
Simplifying an engineering design by removing geometric details can significantly reduce the complexity of downstream tasks of mesh generation and field solution computation.
This novel index naturally fits a feature-based design scenario, and facilitates the need of reusing the computation results in downstream tasks.
Although these inconsistencies can be kept below the scale that is important for visualisation and manufacture, they cause problems for many downstream tasks, making it difficult to use CAD models directly for simulation or advanced geometric analysis, for example.
Does the downstream task define the relevance of the disentanglement to learn?
Commenting in more detail we see in a how every parameter definition has to be repeated for every downstream task, from where it was first defined.
We demonstrate how we transfer supervision from RGB images to depth images as obtained from a range sensors, such as the Microsoft Kinect, for the downstream task of saliency detection.
In other words, the parameter value will need to be passed on all the way from the most downstream task of the workflow up to where it is actually used.
The standard benchmarks for this task do not resemble realistic use cases, and generally assume that downstream task models are built using logistic regression, rather than the complex neural network architectures that are in fact widely employed for language understanding tasks.
