search

fundamentalvision / Uni-Perceiver

Apache License 2.0
266 stars 21 forks source link

Meaning and role of SHARED_TARGETS? #7

Closed tgyy1995 closed 1 year ago

tgyy1995 commented 1 year ago

Thank you for such a wonderful work. Would you please explain the meaning and role of SHARED_TARGETS?

Lechatelia commented 1 year ago

As Uni-Perceiver has no task-specific head (e.g., 1000-classes classification head for Imagenet1k), it will calculate the deep representation for targets (e.g., class names). For open-set classification tasks like Imagenet, the category names are fixed, thus, all GPUs can share the targets. Moreover, the shared targets can be partitioned to different GPUs to save memory costs, which is useful especially for tasks with too many class names, such as ImageNet21k.