Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909060830330880 |
|---|---|
| author | Yuan, Jinyang Chen, Tonglin Shen, Zhimeng Li, Bin Xue, Xiangyang |
| author_facet | Yuan, Jinyang Chen, Tonglin Shen, Zhimeng Li, Bin Xue, Xiangyang |
| contents | Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a multi-object visual scene from multiple viewpoints, humans can perceive the scene compositionally from each viewpoint while achieving the so-called ``object constancy'' across different viewpoints, even though the exact viewpoints are untold. This ability is essential for humans to identify the same object while moving and to learn from vision efficiently. It is intriguing to design models that have a similar ability. In this paper, we consider a novel problem of learning compositional scene representations from multiple unspecified (i.e., unknown and unrelated) viewpoints without using any supervision and propose a deep generative model which separates latent representations into a viewpoint-independent part and a viewpoint-dependent part to solve this problem. During the inference, latent representations are randomly initialized and iteratively updated by integrating the information in different viewpoints with neural networks. Experiments on several specifically designed synthetic datasets have shown that the proposed method can effectively learn from multiple unspecified viewpoints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01922 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints Yuan, Jinyang Chen, Tonglin Shen, Zhimeng Li, Bin Xue, Xiangyang Computer Vision and Pattern Recognition Machine Learning Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a multi-object visual scene from multiple viewpoints, humans can perceive the scene compositionally from each viewpoint while achieving the so-called ``object constancy'' across different viewpoints, even though the exact viewpoints are untold. This ability is essential for humans to identify the same object while moving and to learn from vision efficiently. It is intriguing to design models that have a similar ability. In this paper, we consider a novel problem of learning compositional scene representations from multiple unspecified (i.e., unknown and unrelated) viewpoints without using any supervision and propose a deep generative model which separates latent representations into a viewpoint-independent part and a viewpoint-dependent part to solve this problem. During the inference, latent representations are randomly initialized and iteratively updated by integrating the information in different viewpoints with neural networks. Experiments on several specifically designed synthetic datasets have shown that the proposed method can effectively learn from multiple unspecified viewpoints. |
| title | Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.01922 |