When Slots Compete: Slot Merging in Object-Centric Learning

2026-03-11

AI Summary

This work addresses the challenge in object-centric learning where a fixed number of slots often leads to multiple slots competing for the same entity due to overlapping regions, hindering effective object separation. To resolve this, the authors propose a lightweight slot-merging mechanism that requires no additional learnable components. By leveraging a Soft-IoU metric to dynamically assess the overlap between slot attention maps, redundant slots are adaptively merged, while a centroid-based update strategy preserves gradient flow during training. This approach enables adaptive slot pruning without compromising representational capacity. Seamlessly integrated into the DINOSAUR framework, the method significantly outperforms existing adaptive approaches on object discovery and segmentation benchmarks, yielding improved mask quality and enhanced object factorization performance.

Technology Category

• Search and Optimization: Learning to Search
• Computer Vision: Object Detection & Categorization
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are combined into an output, but the slot set is typically fixed: the number of slots is chosen upfront and slots are only refined. This can lead to multiple slots competing for overlapping regions of the same entity rather than focusing on distinct regions. We introduce slot merging: a drop-in, lightweight operation on the slot set that merges overlapping slots during training. We quantify overlap with a Soft-IoU score between slot-attention maps and combine selected pairs via a barycentric update that preserves gradient flow. Merging follows a fixed policy, with the decision threshold inferred from overlap statistics, requiring no additional learnable modules. Integrated into the established feature-reconstruction pipeline of DINOSAUR, the proposed method improves object factorization and mask quality, surpassing other adaptive methods in object discovery and segmentation benchmarks.

Problem

• slot merging
• object-centric learning
• slot competition
• overlapping regions
• object factorization

Innovation

• slot merging
• object-centric learning
• Soft-IoU
• barycentric update
• DINOSAUR