Sparse training with fixed per-neuron top-magnitude masks reduces the measured incidence of gradient conflict and improves multi-task learning performance across several backbones and gradient manipulation methods.
Sam fails to segment anything? – sam- adapter: Adapting sam in underperformed scenes: Camou- flage, shadow, and more, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective
Sparse training with fixed per-neuron top-magnitude masks reduces the measured incidence of gradient conflict and improves multi-task learning performance across several backbones and gradient manipulation methods.