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
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.