MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915539347046400 |
|---|---|
| author | Liu, Hongjia Zhao, Rongzhen Chen, Haohan Pajarinen, Joni |
| author_facet | Liu, Hongjia Zhao, Rongzhen Chen, Haohan Pajarinen, Joni |
| contents | Learning object-level, structured representations is widely regarded as a key to better generalization in vision and underpins the design of next-generation Pre-trained Vision Models (PVMs). Mainstream Object-Centric Learning (OCL) methods adopt Slot Attention or its variants to iteratively aggregate objects' super-pixels into a fixed set of query feature vectors, termed slots. However, their reliance on a static slot count leads to an object being represented as multiple parts when the number of objects varies. We introduce MetaSlot, a plug-and-play Slot Attention variant that adapts to variable object counts. MetaSlot (i) maintains a codebook that holds prototypes of objects in a dataset by vector-quantizing the resulting slot representations; (ii) removes duplicate slots from the traditionally aggregated slots by quantizing them with the codebook; and (iii) injects progressively weaker noise into the Slot Attention iterations to accelerate and stabilize the aggregation. MetaSlot is a general Slot Attention variant that can be seamlessly integrated into existing OCL architectures. Across multiple public datasets and tasks--including object discovery and recognition--models equipped with MetaSlot achieve significant performance gains and markedly interpretable slot representations, compared with existing Slot Attention variants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20772 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning Liu, Hongjia Zhao, Rongzhen Chen, Haohan Pajarinen, Joni Computer Vision and Pattern Recognition Machine Learning Learning object-level, structured representations is widely regarded as a key to better generalization in vision and underpins the design of next-generation Pre-trained Vision Models (PVMs). Mainstream Object-Centric Learning (OCL) methods adopt Slot Attention or its variants to iteratively aggregate objects' super-pixels into a fixed set of query feature vectors, termed slots. However, their reliance on a static slot count leads to an object being represented as multiple parts when the number of objects varies. We introduce MetaSlot, a plug-and-play Slot Attention variant that adapts to variable object counts. MetaSlot (i) maintains a codebook that holds prototypes of objects in a dataset by vector-quantizing the resulting slot representations; (ii) removes duplicate slots from the traditionally aggregated slots by quantizing them with the codebook; and (iii) injects progressively weaker noise into the Slot Attention iterations to accelerate and stabilize the aggregation. MetaSlot is a general Slot Attention variant that can be seamlessly integrated into existing OCL architectures. Across multiple public datasets and tasks--including object discovery and recognition--models equipped with MetaSlot achieve significant performance gains and markedly interpretable slot representations, compared with existing Slot Attention variants. |
| title | MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.20772 |