Swin-TUNA inserts layer-dependent depthwise-convolution adapters into a frozen Swin-L backbone and reports 50.56 mIoU on FoodSeg103 and 74.94 mIoU on UECFoodPix Complete with 8.13M 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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Swin-TUNA : A Novel PEFT Approach for Accurate Food Image Segmentation
Swin-TUNA inserts layer-dependent depthwise-convolution adapters into a frozen Swin-L backbone and reports 50.56 mIoU on FoodSeg103 and 74.94 mIoU on UECFoodPix Complete with 8.13M trainable parameters.