Metraipolis › archive › dc_0ce53479409f

Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision — arXiv:2608.27877

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27877
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:01.556Z
SHA-256 of the archived text
f5b08eb728adadb490d4427b23fc4b4ec7a302cb354466b06bfce29a21119e2c
Stable URL of this page
https://metraipolis.com/documento/dc_0ce53479409f

How to cite

Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision — arXiv:2608.27877 — arXiv (en), https://arxiv.org/abs/2608.27877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ce53479409f (Metraipolis archive dc_0ce53479409f, sha256 f5b08eb728adadb490d4427b23fc4b4ec7a302cb354466b06bfce29a21119e2c)
BibTeX
@misc{dc0ce53479409f,
  title = {Relational Knowledge Distillation Brings DNN Representations Close Enough to Humans to Be Aligned Without Supervision — arXiv:2608.27877},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27877},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ce53479409f; sha256 f5b08eb728adadb490d4427b23fc4b4ec7a302cb354466b06bfce29a21119e2c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Linking the internal representations of deep neural networks (DNNs) to human mental representations is important for using DNNs as computational models of human vision. Existing DNN representations remain insufficiently similar to human mental representations, which are not directly observable and are therefore commonly measured through large-scale similarity judgments of object images. A natural approach to narrowing this gap is to directly transfer the relational structure of human representations into DNNs, and previous studies have reported improved human-DNN representational similarity. However, whether this improvement holds under stricter evaluation remains untested in two respects: fine-grained alignment at the individual-object level, and generalization to a human embedding derived from a dataset independent of the training data. Here, we employ an unsupervised comparison method, Gromov-Wasserstein optimal transport (GWOT), which estimates human-DNN correspondences from the internal distance structure alone and thereby tests fine-grained alignment. We further assess generalization on a curated test set of concepts non-overlapping with the training data. We show that fine-tuning pre-trained DNNs with Relational Knowledge Distillation (RKD), an established relational transfer method, brings DNNs close enough to humans to be aligned at the individual-object level on this test set. We also show that this improvement is driven by a more human-like global structure, as reflected in the ordering of distances among coarse categories, while the local human-DNN nearest-neighbor overlap rate remains largely unchanged. These findings indicate that relational transfer from humans brings the global structure of pre-trained DNNs close enough to the human structure to enable fine-grained human-DNN alignment without supervision.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2608.27877 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T11:10:05.272Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).