Efficient Transformer Encoders for Mask2Former-style models

arXiv:2404.15244v1 Announce Type: cross
Abstract: Vision transformer based models bring significant improvements for image segmentation tasks. Although these architectures offer powerful capabilities irrespective of specific segmentation tasks, their use of computational resources can be taxing on deployed devices. One way to overcome this challenge is by adapting the computation level to the specific needs of the input image rather than the current one-size-fits-all approach. To this end, we introduce ECO-M2F or EffiCient TransfOrmer Encoders for Mask2Former-style models. Noting that the …

abstract architectures arxiv capabilities challenge computation computational cs.cv cs.lg devices image improvements mask2former resources segmentation style tasks transformer type vision