Metraipolis › archive › dc_fa5ad1edfb23

LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation — arXiv:2610.10722

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10722
License (as archived)
CC0-1.0
Archived
2026-10-09T05:53:52.785Z
SHA-256 of the archived text
afa6a0c733474b8317f1c9e7dea6f60b306f42314e6d88b6c85158574af08241
Stable URL of this page
https://metraipolis.com/documento/dc_fa5ad1edfb23

How to cite

LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation — arXiv:2610.10722 — arXiv (en), https://arxiv.org/abs/2610.10722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa5ad1edfb23 (Metraipolis archive dc_fa5ad1edfb23, sha256 afa6a0c733474b8317f1c9e7dea6f60b306f42314e6d88b6c85158574af08241)
BibTeX
@misc{dcfa5ad1edfb23,
  title = {LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation — arXiv:2610.10722},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10722},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa5ad1edfb23; sha256 afa6a0c733474b8317f1c9e7dea6f60b306f42314e6d88b6c85158574af08241},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have shown considerable success in unsupervised learning of object representations from images. Block-slot attention-based methods extend this framework to attribute representations by assuming a uniform factorization of object representations into attributes, which may be suboptimal and consequently limit the quality of the learned representations. We therefore investigate a framework for jointly discovering object and attribute representations. Our key contribution is leveraging the Linear Representation Hypothesis (LRH), which postulates that composable concepts can be represented as linearly additive subspaces in slot representations. Based on this insight, we propose a probabilistic model connecting images, slots (objects), and blocks (attributes). We present an architecture that leverages block attention to connect attribute representations to slots and incorporates LRH in both object and attribute representation spaces. This architecture effectively optimizes the Evidence Lower Bound (ELBO) of the proposed graphical model. Our experiments demonstrate (i) effective discovery of disentangled object and attribute representations, (ii) empirical evidence for LRH in slot space, and (iii) the ability to perform image editing owing to the disentangled and interpretable nature of the learned representations. Our experiments on multiple datasets demonstrate improvements in DCI scores over state-of-the-art methods.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10722 — 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 2026-10-09T05:47:01.306Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).