Reproduce “Learning from Subjective Ratings Using Auto-Decoded Deep Latent Embeddings” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Bowen Li, Xinping Ren, Ke Yan, Le Lu, Lingyun Huang, Guotong Xie, Jing Xiao, Dar-In Tai and 1 more
ADDLE models how clinician identity influences predictions from routine liver ultrasound images with single-rater labels. It learns a small representation for each clinician and injects it into a shared image model. On biopsy-labeled data from 148 test patients, its greedy virtual-rater output increased normalized partial AUC for severe steatosis from 0.615 to 0.720 versus ResNet-18, in this task and cohort.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.