Circuit duplication on frozen DINOv3 embeddings raises macro F1 to 0.875 on AQUA20, within 1.4 points of supervised ConvNeXt, with class-specific circuits helping 75% of species.
AQUA20: A benchmark dataset for underwater species classification under challenging conditions.Arabian Jour- nal for Science and Engineering
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
-
Inference-Path Optimization via Circuit Duplication in Frozen Visual Transformers for Marine Species Classification
Circuit duplication on frozen DINOv3 embeddings raises macro F1 to 0.875 on AQUA20, within 1.4 points of supervised ConvNeXt, with class-specific circuits helping 75% of species.