QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning

TL;DR

QASA introduces a novel unsupervised object-centric learning method that dynamically selects high-quality slots for improved scene understanding, overcoming limitations of previous K-adaptive approaches by decoupling slot selection from reconstruction.

Contribution

The paper proposes QASA, a new approach that assesses slot quality and dynamically selects high-quality slots, significantly improving over prior K-adaptive methods in object-centric learning.

Findings

QASA outperforms existing K-adaptive methods on synthetic and real datasets.

QASA surpasses K-fixed methods on real-world datasets.

The method effectively improves slot-object binding quality.

Abstract

Slot Attention, an approach that binds different objects in a scene to a set of "slots", has become a leading method in unsupervised object-centric learning. Most methods assume a fixed slot count K, and to better accommodate the dynamic nature of object cardinality, a few works have explored K-adaptive variants. However, existing K-adaptive methods still suffer from two limitations. First, they do not explicitly constrain slot-binding quality, so low-quality slots lead to ambiguous feature attribution. Second, adding a slot-count penalty to the reconstruction objective creates conflicting optimization goals between reducing the number of active slots and maintaining reconstruction fidelity. As a result, they still lag significantly behind strong K-fixed baselines. To address these challenges, we propose Quality-Guided K-Adaptive Slot Attention (QASA). First, we decouple slot selection from reconstruction, eliminating the mutual constraints between the two objectives. Then, we propose an unsupervised Slot-Quality metric to assess per-slot quality, providing a principled signal for fine-grained slot--object binding. Based on this metric, we design a Quality-Guided Slot Selection scheme that dynamically selects a subset of high-quality slots and feeds them into our newly designed gated decoder for reconstruction during training. At inference, token-wise competition on slot attention yields a K-adaptive outcome. Experiments show that QASA substantially outperforms existing K-adaptive methods on both real and synthetic datasets. Moreover, on real-world datasets QASA surpasses K-fixed methods.