pith. the verified trust layer for science. sign in

Explor- ing deep neural networks via layer-peeled model: Minority collapse in imbalanced training.Proceedings of the National Academy of Sciences, 118(43):e2103091118, 2021

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Neural Collapse in Test-Time Adaptation

cs.CV · 2025-12-11 · unverdicted · novelty 7.0

Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.

citing papers explorer

Showing 1 of 1 citing paper.

  • Neural Collapse in Test-Time Adaptation cs.CV · 2025-12-11 · unverdicted · none · ref 4

    Sample-wise neural collapse reveals that feature-classifier misalignment drives TTA degradation under shifts, which NCTTA corrects via hybrid geometric-predictive targets.