DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
-
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.