Learning Aspect Graph Representations from View Sequences

NeurIPS 1989 pp. 258-265

/neurips/1989/seibert1989neurips-learning/

Abstract

In our effort to develop a modular neural system for invariant learn(cid:173) ing and recognition of 3D objects, we introduce here a new module architecture called an aspect network constructed around adaptive axo-axo-dendritic synapses. This builds upon our existing system (Seibert & Waxman, 1989) which processes 20 shapes and classifies t.hem into view categories (i.e., aspects) invariant to illumination, position, orientat.ion, scale, and projective deformations. From a sequence 'of views, the aspect network learns the transitions be(cid:173) tween these aspects, crystallizing a graph-like structure from an initially amorphous network . Object recognition emerges by ac(cid:173) cumulating evidence over multiple views which activate competing object hypotheses.

PDF NeurIPS Semantic Scholar

Cite

Text

Seibert and Waxman. "Learning Aspect Graph Representations from View Sequences." Neural Information Processing Systems, 1989.

Markdown

[Seibert and Waxman. "Learning Aspect Graph Representations from View Sequences." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/seibert1989neurips-learning/)

BibTeX

@inproceedings{seibert1989neurips-learning,
  title     = {{Learning Aspect Graph Representations from View Sequences}},
  author    = {Seibert, Michael and Waxman, Allen M.},
  booktitle = {Neural Information Processing Systems},
  year      = {1989},
  pages     = {258-265},
  url       = {https://mlanthology.org/neurips/1989/seibert1989neurips-learning/}
}