Recent years have witnessed a significant rise in research related to NAS that allows automatically finding deep network architectures. These architectures often achieve better performance than the state-of-the-art methods that have been carefully designed by DL researchers. Although NAS shows promise by exhibiting superior performance on standard benchmarks such as CIFAR-10/100 and ImageNet, the evidence is scarce that they would work equally well on real-world datasets. Moreover, the research has rarely explored vision-based tasks such as pose estimation, activity recognition in videos, generative models, vision-language tasks and real-time vision applications. This gap between published literature for NAS and their performance on real-world datasets/applications is yet to be addressed. The aim of this workshop is to advocate NAS for in-the-wild computer vision across this wide range of tasks and potentially across a range of computing platforms.

The workshop scope includes (but is not limited to),

· Neural architecture search (NAS)

· Challenges in using NAS/HPO for real-world unconstrained datasets and applications

· Application of NAS/HPO in real-time vision applications

· Application of NAS/HPO beyond image classification and object detection

· Meta learning and transfer learning for computer vision

· Learning to learn for computer vision

· NAS/HPO for hardware-aware scenarios

· NAS/HPO combined with model compression