This paper introduces a novel, integrated approach AHA ( A daptive H uman-A ssisted OOD learning) to simultaneously address both OOD generalization and detection through a human-assisted framework by labeling data in the wild.

In many situations, a single demonstration may be correctly interpreted as demonstration ofavariety ofgoals -wecallthisgoalambiguity.

Neural Information Processing Systems http://nips.cc/

For each benchmark, we generate three different training datasets. If the dataset is a sample, then what is the larger set? Is the samplerepresentativeofthe larger set(e.g., geographic coverage)? The provided datasets are self-contained and will remain constant. However, more datasets could be generated using the proposed benchmarking platform.

Many real datasets are hierarchically structured.