Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911916169887744 |
|---|---|
| author | Fan, Ke Bai, Zechen Xiao, Tianjun He, Tong Horn, Max Fu, Yanwei Locatello, Francesco Zhang, Zheng |
| author_facet | Fan, Ke Bai, Zechen Xiao, Tianjun He, Tong Horn, Max Fu, Yanwei Locatello, Francesco Zhang, Zheng |
| contents | Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09196 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Slot Attention: Object Discovery with Dynamic Slot Number Fan, Ke Bai, Zechen Xiao, Tianjun He, Tong Horn, Max Fu, Yanwei Locatello, Francesco Zhang, Zheng Computer Vision and Pattern Recognition Machine Learning Object-centric learning (OCL) extracts the representation of objects with slots, offering an exceptional blend of flexibility and interpretability for abstracting low-level perceptual features. A widely adopted method within OCL is slot attention, which utilizes attention mechanisms to iteratively refine slot representations. However, a major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. This not only necessitates prior knowledge of the dataset but also overlooks the inherent variability in the number of objects present in each instance. To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots based on the content of the data. This is achieved by proposing a discrete slot sampling module that is responsible for selecting an appropriate number of slots from a candidate list. Furthermore, we introduce a masked slot decoder that suppresses unselected slots during the decoding process. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to each instance's complexity, offering the potential for further exploration in slot attention research. Project will be available at https://kfan21.github.io/AdaSlot/ |
| title | Adaptive Slot Attention: Object Discovery with Dynamic Slot Number |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2406.09196 |