Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.
Understanding black-box predictions via influence functions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.
PhiNet adds phonetic interpretability to speaker verification while matching the accuracy of standard black-box models on VoxCeleb, SITW, and LibriSpeech.
citing papers explorer
-
AttriBE: Quantifying Attribute Expressivity in Body Embeddings for Recognition and Identification
Transformer-based ReID embeddings encode BMI most strongly in deeper layers, followed by pitch, gender, and yaw, with pose peaking in middle layers and BMI increasing with depth; cross-spectral settings shift reliance toward structural cues.
-
Label Leakage Attacks in Machine Unlearning: A Parameter and Inversion-Based Approach
Parameter-difference and model-inversion attacks can identify forgotten classes after machine unlearning on standard image datasets.
-
PhiNet: Speaker Verification with Phonetic Interpretability
PhiNet adds phonetic interpretability to speaker verification while matching the accuracy of standard black-box models on VoxCeleb, SITW, and LibriSpeech.