FGMoE combines fine-grained intra-task experts, always-active shared experts, and a global expert layer in a frozen-backbone decoder to improve multi-task dense prediction with fewer trainable parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts
FGMoE combines fine-grained intra-task experts, always-active shared experts, and a global expert layer in a frozen-backbone decoder to improve multi-task dense prediction with fewer trainable parameters.