Slot Attention with Re-Initialization and Self-Distillation

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

8

Series

Proceedings of the 33rd ACM International Conference on Multimedia, pp. 4185-4192

Abstract

Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL typically aggregates object superpixels into slots by iteratively applying competitive cross attention, known as Slot Attention, with the slots as the query. However, once initialized, these slots are reused naively, causing redundant slots to compete with informative ones for representing objects. This often results in objects being erroneously segmented into parts. Additionally, mainstream methods derive supervision signals solely from decoding slots into the input's reconstruction, overlooking potential supervision based on internal information. To address these issues, we propose Slot Attention with re-Initialization and self-Distillation (DIAS): i) We reduce redundancy in the aggregated slots and re-initialize extra aggregation to update the remaining slots; ii) We drive the bad attention map at the first aggregation iteration to approximate the good at the last iteration to enable self-distillation. Experiments demonstrate that DIAS achieves state-of-the-art on OCL tasks like object discovery and recognition, while also improving advanced visual prediction and reasoning. Our source code and model checkpoints are available on https://github.com/Genera1Z/DIAS.

Description

Other note

Citation

Zhao, R, Zhao, Y, Kannala, J & Pajarinen, J 2025, Slot Attention with Re-Initialization and Self-Distillation. in Proceedings of the 33rd ACM International Conference on Multimedia. ACM, pp. 4185-4192, ACM International Conference on Multimedia, Dublin, Ireland, 27/10/2025. https://doi.org/10.1145/3746027.3755339