Unlearnable examples fail under pretraining-finetuning due to semantic filtering by frozen layers, but Shallow Semantic Camouflage restores effectiveness by confining perturbations to semantically valid subspaces.
A style-based generator architecture for generative adversarial networks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
method 1polarities
use method 1representative citing papers
Graph-PiT adds graph priors and a hierarchical GNN to part-based image synthesis to enforce relational constraints and improve structural coherence over vanilla PiT.
The work creates identity-consistent synthetic makeup data via ConsistentBeauty and adapts models to real images using reinforcement learning in RealBeauty, achieving better identity preservation and real-world performance than prior methods.
EMSFD uses Dirichlet-based evidence modeling to capture prediction uncertainty in synthetic face detection and applies uncertainty-driven active learning to achieve 15% higher accuracy than prior methods.
PCMECL improves speech-preserving facial expression manipulation by learning personalized prompts from individual visuals and using feature differencing to align visual and semantic changes from VLMs.
citing papers explorer
-
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
Unlearnable examples fail under pretraining-finetuning due to semantic filtering by frozen layers, but Shallow Semantic Camouflage restores effectiveness by confining perturbations to semantically valid subspaces.
-
Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors
Graph-PiT adds graph priors and a hierarchical GNN to part-based image synthesis to enforce relational constraints and improve structural coherence over vanilla PiT.
-
From Synthetic to Real: Toward Identity-Consistent Makeup Transfer with Synthetic and Real Data
The work creates identity-consistent synthetic makeup data via ConsistentBeauty and adapts models to real images using reinforcement learning in RealBeauty, achieving better identity preservation and real-world performance than prior methods.
-
Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning
EMSFD uses Dirichlet-based evidence modeling to capture prediction uncertainty in synthetic face detection and applies uncertainty-driven active learning to achieve 15% higher accuracy than prior methods.
-
Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation
PCMECL improves speech-preserving facial expression manipulation by learning personalized prompts from individual visuals and using feature differencing to align visual and semantic changes from VLMs.