Primus and PrimusV2 are Transformer-centric models that match or exceed nnU-Net and top CNNs on nine 3D medical segmentation datasets by enforcing attention usage.
Per- pixel classification is not all you need for semantic segmen- tation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
GCLIP improves TF-OVSS by reshaping last-block attention via fusion of global-token block attention with Query-Query attention and applying channel suppression to Value embeddings, outperforming prior methods on five benchmarks.
citing papers explorer
-
Primus: Enforcing Attention Usage for 3D Medical Image Segmentation
Primus and PrimusV2 are Transformer-centric models that match or exceed nnU-Net and top CNNs on nine 3D medical segmentation datasets by enforcing attention usage.
-
Rethinking the Global Knowledge of CLIP in Training-Free Open-Vocabulary Semantic Segmentation
GCLIP improves TF-OVSS by reshaping last-block attention via fusion of global-token block attention with Query-Query attention and applying channel suppression to Value embeddings, outperforming prior methods on five benchmarks.