Adaptive Slot Attention: Object Discovery with Dynamic Slot Number

Ke Fan, Zechen Bai, Tianjun Xiao, Tong He, Max Horn, Yanwei Fu, Francesco Locatello, Zheng Zhang

Keywords: Object-centric Learning, Slot Attention, Gumbel-Softmax

Abstract:

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.
To overcome this fundamental limitation, we present a novel complexity-aware object auto-encoder framework. Within this framework, we introduce an adaptive slot attention 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.
To validate the effectiveness of our framework, we conduct extensive evaluations on object discovery tasks using diverse datasets. The experimental results demonstrate that our framework achieves performance that is comparable to or even surpasses the best-performing fixed-slot models in evaluation. Moreover, our analysis substantiates that our method exhibits the capability to dynamically adapt the slot number according to the complexity of each specific instance. The instance-level adaptability offers potential for further exploration in slot attention research.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1880