WoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identification
Wood-image benchmarks can yield optimistic estimates when images from the same tree occur in both training and test sets.
ProofPaper ↗
Key points
- WoodBR-Cross contains 4,875 transverse-surface images in 38 operational taxonomic classes, linked to 303 distinct trees identified by numeric catalogue witness codes (codigos-testemunho) in the Brazilian Forest Service collection.
- A species-level subset comprises 3,406 images, 20 classes and 214 trees.
- Three tasks compare duplicate-aware image partitions for all classes (A), image partitions for the species subset (B1), and individual-tree-disjoint partitions for that subset (B2).
- Validation-selected ConvNeXt-Tiny achieved B2 tree-level macro-F1 of 0.8621 +/- 0.0317; frozen DINOv2 features yielded 0.9000 +/- 0.0722.
Sources (1)
- [1]WoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identificationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:57 PM
Wood-image benchmarks can yield optimistic estimates when images from the same tree occur in both training and test sets.
WoodBR-Cross contains 4,875 transverse-surface images in 38 operational taxonomic classes, linked to 303 distinct trees identified by numeric catalogue witness codes (codigos-testemunho) in the Brazilian Forest Service collection.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder
- Oct 8, 2026Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
- Oct 8, 2026MCL: Meta Convolution Layer
- Oct 8, 2026One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- Oct 7, 2026On the Necessity of Attention-FFN Split in Vision Transformers
- Oct 7, 2026ORCA: Hunting Compositional Failures in Text-to-Image Diffusion