CVPR24-NAS
Fifth workshop on Neural Architecture Search
请输入标题
There is a lot of evidence that Neural Architecture Search can produce excellent models capable of ML tasks on well-known datasets, that is, datasets like CIFAR-10 and ImageNet where years of research have created a set of best practices to follow to achieve good results. This leads us to wonder, are we overfitting our NAS algorithms to well-known datasets?
We want to investigate the "real-world" use case of NAS, that is, searching for a state-of-the-art architecture on an entirely novel dataset. In such a case, there is no existing set of best practices to build from, nor extensive research into optimal architectural patterns, augmentation policies, or hyperparameter selection. In essence, we are asking how well NAS pipelines can work “out-of-the-box” with little-to-no time for tuning. To explore this, we’ve designed this competition to evaluate how well a NAS pipeline fares over unseen novel tasks and datasets.
In this competition, you will be asked to design a NAS pipeline, namely a data processor, a NAS algorithm, and a training policy. This pipeline will then be evaluated on our servers over a number of completely novel datasets: the challenge is to design a pipeline that is flexible enough to be competitive regardless of the datasets provided to it.