Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
EfficientNetB5 with CBAM reaches 93.3% accuracy on a 1,366-image peach leaf damage dataset and EfficientNetB3 with CBAM reaches 93% macro F1 after transfer to a 180-image local domain.
citing papers explorer
-
Editing Models with Task Arithmetic
Task vectors from weight differences allow arithmetic operations to edit pre-trained models, improving multiple tasks simultaneously and enabling analogical inference on unseen tasks.
-
Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift
EfficientNetB5 with CBAM reaches 93.3% accuracy on a 1,366-image peach leaf damage dataset and EfficientNetB3 with CBAM reaches 93% macro F1 after transfer to a 180-image local domain.