Skip to content

Latest commit

 

History

History
7 lines (4 loc) · 356 Bytes

220615 A Unified Sequence Interface for Vision Tasks.md

File metadata and controls

7 lines (4 loc) · 356 Bytes

https://arxiv.org/abs/2206.07669

A Unified Sequence Interface for Vision Tasks (Ting Chen, Saurabh Saxena, Lala Li, Tsung-Yi Lin, David J. Fleet, Geoffrey Hinton)

예상하던 그것이 나왔네요. multitask pix2seq. instance segmentation도 좌표 예측으로 통합이 가능하군요.

#multitask #object_detection #instance_segmentation #keypoint