Learning Versatile Neural Architectures by Propagating Network Codes. (arXiv:2103.13253v2 [cs.CV] UPDATED)

This work explores how to design a single neural network capable of adapting
to multiple heterogeneous vision tasks, such as image segmentation, 3D
detection, and video recognition. This goal is challenging because both network
architecture search (NAS) spaces and methods in different tasks are
inconsistent. We solve this challenge from both sides. We first introduce a
unified design space for multiple tasks and build a multitask NAS benchmark
(NAS-Bench-MR) on many widely used datasets, including ImageNet, Cityscapes,
KITTI, and HMDB51. …

arxiv cv learning network neural architectures