Task Indicating Transformer for Task-conditional Dense Predictions
This work addresses a critical limitation in efficient multi-task learning for dense predictions, offering an incremental improvement over existing task-conditional models.
The paper tackles the challenge of learning task-agnostic and task-specific representations in multi-task dense prediction by introducing the Task Indicating Transformer (TIT), which surpasses state-of-the-art methods on benchmarks like NYUD-v2 and PASCAL-Context.
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 transformer block, which incorporates a Task Indicating Matrix through matrix decomposition, thereby enhancing long-range dependency modeling and parameter-efficient feature adaptation by capturing intra- and inter-task features. Moreover, we propose a Task Gate Decoder module that harnesses a Task Indicating Vector and gating mechanism to facilitate adaptive multi-scale feature refinement guided by task embeddings. Experiments on two public multi-task dense prediction benchmarks, NYUD-v2 and PASCAL-Context, demonstrate that our approach surpasses state-of-the-art task-conditional methods.