Task Indicating Transformer for Task-conditional Dense Predictions

arXiv:2403.00327v1 Announce Type: new
Abstract: The task-conditional model is a distinctive stream for efficient multi-task learning. Existing works encounter a critical limitation in learning task-agnostic and task-specific representations, primarily due to shortcomings in global context modeling arising from CNN-based architectures, as well as a deficiency in multi-scale feature interaction within the decoder. In this paper, we introduce a novel task-conditional framework called Task Indicating Transformer (TIT) to tackle this challenge. Our approach designs a Mix Task Adapter module within the …

abstract architectures arxiv cnn context cs.cv decoder feature global modeling multi-task learning predictions scale the decoder transformer type