I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers

• URL: http://arxiv.org/abs/2604.09942v1
• Date: Fri, 10 Apr 2026 22:47:11 GMT
• Title: I Walk the Line: Examining the Role of Gestalt Continuity in Object Binding for Vision Transformers
• Abstract summary: We show that binding probes are sensitive to continuity across a wide range of pretrained vision transformers.<n>Next, we uncover particular attention heads that track continuity, and show that these heads generalize across datasets.<n>We ablate these attention heads, and show that they often contribute to producing representations that encode object binding.
• Score: 5.684409853507593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object binding is a foundational process in visual cognition, during which low-level perceptual features are joined into object representations. Binding has been considered a fundamental challenge for neural networks, and a major milestone on the way to artificial models with flexible visual intelligence. Recently, several investigations have demonstrated evidence that binding mechanisms emerge in pretrained vision models, enabling them to associate portions of an image that contain an object. The question remains: how are these models binding objects together? In this work, we investigate whether vision models rely on the principle of Gestalt continuity to perform object binding, over and above other principles like similarity and proximity. Using synthetic datasets, we demonstrate that binding probes are sensitive to continuity across a wide range of pretrained vision transformers. Next, we uncover particular attention heads that track continuity, and show that these heads generalize across datasets. Finally, we ablate these attention heads, and show that they often contribute to producing representations that encode object binding.

Related papers

• Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers? [11.078284195461578]
  We show that object binding emerges in pre-trained Vision Transformers (ViTs)<n>We find that IsSameObject is encoded in a low-dimensional subspace on top of object features, and that this signal actively guides attention.<n>Our findings challenge the view that ViTs lack object binding and highlight how symbolic knowledge of "which parts belong together" emerges naturally in a connectionist system.
  arXiv  Detail & Related papers  (2025-10-28T17:57:05Z)
• Object Concepts Emerge from Motion [24.73461163778215]
  We propose a biologically inspired framework for learning object-centric visual representations in an unsupervised manner.<n>Our key insight is that motion boundary serves as a strong signal for object-level grouping.<n>Our framework is fully label-free and does not rely on camera calibration, making it scalable to large-scale unstructured video data.
  arXiv  Detail & Related papers  (2025-05-27T18:09:02Z)
• Binding Dynamics in Rotating Features [72.80071820194273]
  We propose an alternative "cosine binding" mechanism, which explicitly computes the alignment between features and adjusts weights accordingly. This allows us to draw direct connections to self-attention and biological neural processes, and to shed light on the fundamental dynamics for object-centric representations to emerge in Rotating Features.
  arXiv  Detail & Related papers  (2024-02-08T12:31:08Z)
• Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Prior [88.9319150230121]
  Object-centric vision aims to construct an explicit representation of the objects in a scene. We incorporate a spatial-locality prior into state-of-the-art object-centric vision models. We obtain significant improvements in segmenting objects in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-05-31T04:35:50Z)
• SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition [35.4163266882568]
  We introduce Self-Supervised Learning Over Sets (SOS) to pre-train a generic Objects In Contact (OIC) representation model. Our OIC significantly boosts the performance of multiple state-of-the-art video classification models.
  arXiv  Detail & Related papers  (2022-04-10T23:27:19Z)
• KINet: Unsupervised Forward Models for Robotic Pushing Manipulation [8.572983995175909]
  We introduce KINet -- an unsupervised framework to reason about object interactions based on a keypoint representation. Our model learns to associate objects with keypoint coordinates and discovers a graph representation of the system. By learning to perform physical reasoning in the keypoint space, our model automatically generalizes to scenarios with a different number of objects.
  arXiv  Detail & Related papers  (2022-02-18T03:32:08Z)
• Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects [73.23249640099516]
  We learn both the appearance and the structure of previously unseen articulated objects by observing them move from multiple views. Our insight is that adjacent parts that move relative to each other must be connected by a joint. We show that our method works for different structures, from quadrupeds, to single-arm robots, to humans.
  arXiv  Detail & Related papers  (2021-12-21T16:37:48Z)
• Constellation: Learning relational abstractions over objects for compositional imagination [64.99658940906917]
  We introduce Constellation, a network that learns relational abstractions of static visual scenes. This work is a first step in the explicit representation of visual relationships and using them for complex cognitive procedures.
  arXiv  Detail & Related papers  (2021-07-23T11:59:40Z)
• Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
  We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
  arXiv  Detail & Related papers  (2020-10-19T12:36:11Z)
• Visual Relationship Detection with Visual-Linguistic Knowledge from Multimodal Representations [103.00383924074585]
  Visual relationship detection aims to reason over relationships among salient objects in images. We propose a novel approach named Visual-Linguistic Representations from Transformers (RVL-BERT) RVL-BERT performs spatial reasoning with both visual and language commonsense knowledge learned via self-supervised pre-training.
  arXiv  Detail & Related papers  (2020-09-10T16:15:09Z)

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.