A Unified Sequence Interface for Vision Tasks. (arXiv:2206.07669v1 [cs.CV])

Web: http://arxiv.org/abs/2206.07669

While language tasks are naturally expressed in a single, unified, modeling
framework, i.e., generating sequences of tokens, this has not been the case in
computer vision. As a result, there is a proliferation of distinct
architectures and loss functions for different vision tasks. In this work we
show that a diverse set of "core" computer vision tasks can also be unified if
formulated in terms of a shared pixel-to-sequence interface. We focus on four
tasks, namely, object detection, instance segmentation, …

arxiv cv vision