Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.
Benchmarking neu- ral network robustness to common corruptions and perturba- tions.Proceedings of the International Conference on Learn- ing Representations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
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.