# HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition

Source: [HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition](<https://www.sota2.com/research/paper/6a507caa32fb93731487698b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-11T05:00:01.218Z

Authors: Neelu Madan, Rongzhen Zhao, Andreas Mogelmose, Juho Kannala, Joni Pajarinen, Graham W. Taylor, Thomas B. Moeslund

Published: 2026-07-09T08:53:15.000Z

## Abstract

Slot attention is a powerful framework for object-centric learning, decomposing visual scenes into latent slots through iterative competitive attention. However, existing methods share two critical limitations: they decompose scenes into a flat set of slots at a single granularity, and this decomposition is based on appearance rather than semantics. Yet humans understand scenes through semantic hierarchies: separating foreground from background, recognizing object categories, and identifying individual instances. Crucially, such semantic hierarchies cannot emerge without supervision, because category names are human constructs, not visual patterns. We propose Hierarchical Slot Attention (HSA), which learns multi-granularity semantic scene decomposition from a single model. HSA decomposes scenes at three levels: holistic (foreground/background), semantic (object categories), and panoptic (individual instances). Using only 10\\% labeled data, combined with hierarchical alignment loss, HSA learns all three levels jointly. We further introduce grouping purity and containment to measure whether the hierarchy is encoded in representation space, not just output masks. Experiments on COCO and PASCAL VOC demonstrate that HSA outperforms the strongest flat baseline by up to \\textbf{$+$41.5} ARI at holistic, \\textbf{$+$14.6} at semantic, and \\textbf{$+$10.4} at panoptic level on COCO, with even larger gains on Pascal VOC, while requiring a single model instead of three. Code will be made available upon acceptance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.08249>)

[PDF](<https://arxiv.org/pdf/2607.08249.pdf>)