GAEor discovers category-specific geometric attributes via self-supervision to achieve new state-of-the-art ultra-fine-grained visual categorization results on five benchmarks in data-limited settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data
GAEor discovers category-specific geometric attributes via self-supervision to achieve new state-of-the-art ultra-fine-grained visual categorization results on five benchmarks in data-limited settings.