When Slots Compete: Slot Merging in Object-Centric Learning

• URL: http://arxiv.org/abs/2603.11246v1
• Date: Wed, 11 Mar 2026 19:12:59 GMT
• Title: When Slots Compete: Slot Merging in Object-Centric Learning
• Abstract summary: 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.<n>We introduce slot merging: a drop-in, lightweight operation on the slot set that merges overlapping slots during training.<n>We quantify overlap with a Soft-IoU score between slot-attention maps and combine selected pairs via a barycentric update that preserves flow.
• Score: 5.298949136750754
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences [71.45325481648995]
  MeshLoom is a feed-forward registration network that reconstructs deformations across mesh sequences.<n>We show that MeshLoom achieves state-of-the-art results on non-rigid registration.
  arXiv  Detail & Related papers  (2026-06-15T17:51:38Z)
• Selective Synergistic Learning for Video Object-Centric Learning [43.27149574230564]
  We propose Selective Synergistic Learning (SSync) for slot-based object-centric learning.<n>SSync prevents patchtopatch alignment by error propagation by only the most reliable cues.<n>Also, SSync improves decomposition quality and serves as a versatile, plugand-play module.
  arXiv  Detail & Related papers  (2026-06-14T00:51:33Z)
• QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learning [80.82392186401354]
  Slot Attention is an approach that binds different objects in a scene to a set of "slots"<n>Previous K-adaptive methods do not explicitly constrain slot-binding quality.<n>We propose Quality-Guided K-Adaptive Slot Attention (QASA)
  arXiv  Detail & Related papers  (2026-01-19T10:42:07Z)
• Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment [83.56510119503265]
  Slot Attention (SA) with pretrained diffusion models has recently shown promise for object-centric learning (OCL), but suffers from slot entanglement and weak alignment between object slots and image content.<n>We propose Contrastive Object-centric Diffusion Alignment (CODA), a simple extension that (i) employs register slots to absorb residual attention and reduce interference between object slots, and (ii) applies a contrastive alignment loss to explicitly encourage slot-image correspondence.
  arXiv  Detail & Related papers  (2026-01-03T16:10:18Z)
• Slot Attention with Re-Initialization and Self-Distillation [33.38373596185185]
  We propose Slot Attention with re-Initialization and self-Distillation (DIAS) for object discovery and recognition.<n>DIAS achieves state-of-the-art on OCL tasks like object discovery and recognition, while also improving advanced visual prediction and reasoning.
  arXiv  Detail & Related papers  (2025-07-31T17:41:18Z)
• MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning [17.083645139372912]
  We introduce MetaSlot, a plug-and-play Slot Attention variant that adapts to variable object counts.<n>We show that MetaSlot achieves significant performance gains and markedly interpretable slot representations, compared with existing Slot Attention variants.
  arXiv  Detail & Related papers  (2025-05-27T06:23:03Z)
• Adaptive Slot Attention: Object Discovery with Dynamic Slot Number [64.45419820717754]
  A major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models.
  arXiv  Detail & Related papers  (2024-06-13T14:55:11Z)
• Enhancing Interpretable Object Abstraction via Clustering-based Slot Initialization [17.25953277219166]
  We present a new method for object-centric representations using slots. Our method outperforms prior works consistently. We evaluate our method on object discovery and novel view synthesis tasks with various datasets.
  arXiv  Detail & Related papers  (2023-08-22T11:48:43Z)
• Divided Attention: Unsupervised Multi-Object Discovery with Contextually Separated Slots [65.302728042116]
  We investigate the emergence of objects in visual perception in the absence of any semantic annotation.<n>The resulting model has received no supervision, does not use any pre-trained features, and yet it can segment the domain of an image into multiple moving regions.<n>The resulting motion segmentation method can handle an unknown and varying number of objects in real-time.
  arXiv  Detail & Related papers  (2023-04-04T00:26:13Z)
• Augmenting Convolutional networks with attention-based aggregation [55.97184767391253]
  We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth) It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption.
  arXiv  Detail & Related papers  (2021-12-27T14:05:41Z)
• A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation [68.10621089649486]
  We propose Attention Aggregation based Feature Pyramid Network (A2-FPN) to improve multi-scale feature learning. A2-FPN achieves an improvement of 2.0% and 1.4% mask AP when integrated into the strong baselines such as Cascade Mask R-CNN and Hybrid Task Cascade.
  arXiv  Detail & Related papers  (2021-05-07T11:51:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.