Transfer learning with pre-training on large-scale datasets has played an
increasingly significant role in computer vision and natural language
processing recently. However, as there exist numerous application scenarios
that have distinctive demands such as certain latency constraints and
specialized data distributions, it is prohibitively expensive to take advantage
of large-scale pre-training for per-task requirements. In this paper, we focus
on the area of object detection and present a transfer learning system named
GAIA, which could automatically and efficiently give birth to customized
solutions according to heterogeneous downstream needs. GAIA is capable of
providing powerful pre-trained weights, selecting models that conform to
downstream demands such as latency constraints and specified data domains, and
collecting relevant data for practitioners who have very few datapoints for
their tasks. With GAIA, we achieve promising results on COCO, Objects365, Open
Images, Caltech, CityPersons, and UODB which is a collection of datasets
including KITTI, VOC, WiderFace, DOTA, Clipart, Comic, and more. Taking COCO as
an example, GAIA is able to efficiently produce models covering a wide range of
latency from 16ms to 53ms, and yields AP from 38.2 to 46.5 without whistles and
bells. To benefit every practitioner in the community of object detection, GAIA
is released at this https URL

本文提出了一个名为 GAIA 的转移学习系统，可根据异构下游需求自动有效地创建定制的解决方案，包括选择符合下游需求的模型和提供强大的预训练权重，同时还收集与任务相关的数据。GAIA 在多个数据集上的检测结果表明其能够高效地生成覆盖从 16ms 到 53ms 的广泛延迟范围的模型，并在不进行任何优化的情况下，取得了 38.2 到 46.5 的 AP，为目标检测领域的从业人员提供了一种简单而有效的解决方案。