Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection
This work reframe anatomical landmark detection as a pixel-level contrastive representation learning problem, matching dense pixel embeddings with landmark prototypes, leading to more discriminative heatmaps compared to the traditional heatmap regression paradigm, leading to improved discrimination between vertebral co...
A. Daridon, Sofiane Sifaoui, A. Assi et al.
· 0 citations