Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
Measuring robustness to natural distribution shifts in image classification
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Pretraining data determines loss-to-loss scaling laws in LLMs, while model size, optimization, tokenizer, and architecture have limited impact.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Pretraining data determines loss-to-loss scaling laws in LLMs, while model size, optimization, tokenizer, and architecture have limited impact.