Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
An image is worth 16x16 words: Transformers for image recognition at scale.ICLR, 2021
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
citing papers explorer
-
Neural Collapse in Test-Time Adaptation
Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
-
Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.