Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
author Sandler, M
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
baseline 1polarities
baseline 1representative citing papers
MP-IB uses an 8x information asymmetry via FP16 trait heads and INT4 state heads to disentangle speaker identity from agitation in voice biomarkers, outperforming larger models on edge devices with low latency and suppressed identity leakage.
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
A novel MIL architecture predicts zero-inflated beta parameters for TPS distributions in NSCLC using slide-level supervision.
A physics-informed CNN predicts pore-scale velocity fields from geometry and serves as a warm-start to accelerate Lattice-Boltzmann solvers in over 90% of tested cases.
EfficientNetB5 with CBAM reaches 93.3% accuracy on a 1,366-image peach leaf damage dataset and EfficientNetB3 with CBAM reaches 93% macro F1 after transfer to a 180-image local domain.
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.
-
Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection
MP-IB uses an 8x information asymmetry via FP16 trait heads and INT4 state heads to disentangle speaker identity from agitation in voice biomarkers, outperforming larger models on edge devices with low latency and suppressed identity leakage.
-
Privatar: Scalable Privacy-preserving Multi-user VR via Secure Offloading
Privatar uses horizontal frequency partitioning and distribution-aware minimal perturbation to enable private offloading of VR avatar reconstruction, supporting 2.37x more users with modest overhead.
-
Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC
A novel MIL architecture predicts zero-inflated beta parameters for TPS distributions in NSCLC using slide-level supervision.
-
Physics-informed convolutional neural networks for fluid flow through porous media
A physics-informed CNN predicts pore-scale velocity fields from geometry and serves as a warm-start to accelerate Lattice-Boltzmann solvers in over 90% of tested cases.
-
Attention mechanisms and transfer learning for robust peach leaf damage classification under domain shift
EfficientNetB5 with CBAM reaches 93.3% accuracy on a 1,366-image peach leaf damage dataset and EfficientNetB3 with CBAM reaches 93% macro F1 after transfer to a 180-image local domain.