Search Results for author:
Found 3 papers, 2 papers with code
LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP
In this work, we propose and examine from convex-optimization perspectives a generalization of the standard LP baseline, in which the linear classifier weights are learnable functions of the text embedding, with class-wise multipliers blending image and text knowledge.
Comparing 3D deformations between longitudinal daily CBCT acquisitions using CNN for head and neck radiotherapy toxicity prediction
Accuracies of 85. 8% and 75. 3% was found for radionecrosis and hospitalization, respectively, with similar performance as early as after the first week of treatment.
Beyond pixel-wise supervision for segmentation: A few global shape descriptors might be surprisingly good!
We also found that shape descriptors can be a valid way to encode anatomical priors about the task, enabling to leverage expert knowledge without additional annotations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
