Author

Tanya Y. Berger-Wolf

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Mind the Tail: Data Selection Through Sparse Concepts

Data selection reallocates training support across visual concepts, including objects, attributes, color, texture, and backgrounds. Different allocation strategies may produce varied downstream model behavior, especially for tail concepts supported by only a few samples. Discarding them can hurt test-time robustness, w...

Zi-Heng Zhang, Neha Hulkund, Colin Lee et al. · 0 citations

#machine learning Jun 2026

Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification

This work proposes to restrict contrastive comparisons to categories within the same taxonomic level, and adopts a group-balanced design, ensuring each taxonomic level receives adequate optimization and improves both hierarchical consistency and classification accuracy from coarse to fine granularity.

Zhi-Yuan Tao, S. Sastry, Matthew J. Thompson et al. · arXiv.org · 0 citations