How PARTs assemble into wholes: Learning the relative composition of images

• URL: http://arxiv.org/abs/2506.03682v1
• Date: Wed, 04 Jun 2025 08:12:18 GMT
• Title: How PARTs assemble into wholes: Learning the relative composition of images
• Abstract summary: spatial-aware pretext tasks have been actively explored in self-supervised learning.<n> grid-based approaches fall short of capturing the fluid and continuous nature of real-world object compositions.<n>We introduce PART, a self-supervised learning approach that leverages continuous relative transformations between off-grid patches.
• Score: 25.06788919709452
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The composition of objects and their parts, along with object-object positional relationships, provides a rich source of information for representation learning. Hence, spatial-aware pretext tasks have been actively explored in self-supervised learning. Existing works commonly start from a grid structure, where the goal of the pretext task involves predicting the absolute position index of patches within a fixed grid. However, grid-based approaches fall short of capturing the fluid and continuous nature of real-world object compositions. We introduce PART, a self-supervised learning approach that leverages continuous relative transformations between off-grid patches to overcome these limitations. By modeling how parts relate to each other in a continuous space, PART learns the relative composition of images-an off-grid structural relative positioning process that generalizes beyond occlusions and deformations. In tasks requiring precise spatial understanding such as object detection and time series prediction, PART outperforms strong grid-based methods like MAE and DropPos, while also maintaining competitive performance on global classification tasks with minimal hyperparameter tuning. By breaking free from grid constraints, PART opens up an exciting new trajectory for universal self-supervised pretraining across diverse datatypes-from natural images to EEG signals-with promising potential in video, medical imaging, and audio.

Related papers

• AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning [52.47988016454267]
  Vision-Language-Action (VLA) models excel at end-to-end robotic manipulation but struggle with out-of-distribution (OOD) generalization.<n>We identify two mutually reinforcing modes: emphtrajectory overfitting, where models overfit to holistic trajectory patterns rather than compositional sub-skill semantics; and emphperceptual shortcut, where action tokens over-rely on wrist-view textures at the expense of global spatial grounding.<n>We introduce textbfAC-VLA, a plug-and-play Action Compositional learning
  arXiv  Detail & Related papers  (2026-07-17T07:51:03Z)
• `Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation [16.700937089524803]
  Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames.<n>We propose a self-supervised framework, Cross-Temporal Consistency and Clustering, that learns part-aware representations by combining attention-guided token selection with lightweight temporal clustering.
  arXiv  Detail & Related papers  (2026-07-08T10:13:20Z)
• Compositional Motion Generation from Demonstration with Object-Centric Neural Fields [1.4916971861796382]
  We propose a generative learning-from-demonstration framework that enables compositional modeling of robotic behavior.<n>We render scenes from object-centric neural representations that integrate canonical neural fields with latent-conditioned deformations.<n>In simulation, long-horizon manipulation tasks are successfully completed using the proposed model.
  arXiv  Detail & Related papers  (2026-07-08T08:20:24Z)
• Learning to Perceive "Where": Spatial Pretext Tasks for Robust Self-Supervised Learning [17.753167530453997]
  We introduce Spatial Prediction, a spatially aware pretext regression task that predicts the relative position and scale between a pair of disentangled local views from the same image.<n>By modeling part-to-part relationships in a continuous geometric space, SP encourages representations to capture fine-grained spatial dependencies.<n>Experiments show consistent improvements across image recognition, fine-grained classification, semantic segmentation, and depth estimation, as well as substantial gains in out-of-distribution for object recognition.
  arXiv  Detail & Related papers  (2026-05-11T04:15:34Z)
• Self-supervised structured object representation learning [2.747398258852965]
  Self-supervised learning has emerged as a powerful technique for learning visual representations.<n>We propose a self-supervised approach that builds structured visual representations by combining semantic grouping, instance level separation, and hierarchical structuring.<n>Our approach, based on a novel ProtoScale module, captures visual elements across multiple spatial scales.
  arXiv  Detail & Related papers  (2025-08-27T13:28:05Z)
• IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments [56.85804719947]
  We present IAAO, a framework that builds an explicit 3D model for intelligent agents to gain understanding of articulated objects in their environment through interaction.<n>We first build hierarchical features and label fields for each object state using 3D Gaussian Splatting (3DGS) by distilling mask features and view-consistent labels from multi-view images.<n>We then perform object- and part-level queries on the 3D Gaussian primitives to identify static and articulated elements, estimating global transformations and local articulation parameters along with affordances.
  arXiv  Detail & Related papers  (2025-04-09T12:36:48Z)
• Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Prediction [61.484280369655536]
  Camera-based 3D Semantic Occupancy Prediction (SOP) is crucial for understanding complex 3D scenes from limited 2D image observations.<n>Existing SOP methods typically aggregate contextual features to assist the occupancy representation learning.<n>We introduce a new Hierarchical context alignment paradigm for a more accurate SOP (Hi-SOP)
  arXiv  Detail & Related papers  (2024-12-11T09:53:10Z)
• Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation [47.047267066525265]
  We introduce a novel approach that incorporates object-level contextual knowledge within images.<n>Our proposed approach achieves state-of-the-art performance with strong generalizability across diverse datasets.
  arXiv  Detail & Related papers  (2024-11-26T06:34:48Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation [5.476136494434766]
  We introduce EiCue, a technique providing semantic and structural cues through an eigenbasis derived from semantic similarity matrix. We guide our model to learn object-level representations with intra- and inter-image object-feature consistency. Experiments on COCO-Stuff, Cityscapes, and Potsdam-3 datasets demonstrate the state-of-the-art USS results.
  arXiv  Detail & Related papers  (2024-03-03T11:24:16Z)
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection [70.11264880907652]
  Recent object (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. We propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and camouflaged zooming in and out. Our framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks.
  arXiv  Detail & Related papers  (2023-10-31T06:11:23Z)
• Mitigating the Effect of Incidental Correlations on Part-based Learning [50.682498099720114]
  Part-based representations could be more interpretable and generalize better with limited data. We present two innovative regularization methods for part-based representations. We exhibit state-of-the-art (SoTA) performance on few-shot learning tasks on benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-30T13:44:48Z)
• DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization [67.85434518679382]
  We present DynaVol, a 3D scene generative model that unifies geometric structures and object-centric learning. The key idea is to perform object-centric voxelization to capture the 3D nature of the scene. voxel features evolve over time through a canonical-space deformation function, forming the basis for global representation learning.
  arXiv  Detail & Related papers  (2023-04-30T05:29:28Z)
• Robust and Controllable Object-Centric Learning through Energy-based Models [95.68748828339059]
  ours is a conceptually simple and general approach to learning object-centric representations through an energy-based model. We show that ours can be easily integrated into existing architectures and can effectively extract high-quality object-centric representations.
  arXiv  Detail & Related papers  (2022-10-11T15:11:15Z)
• Self-supervised Correlation Mining Network for Person Image Generation [9.505343361614928]
  Person image generation aims to perform non-rigid deformation on source images. We propose a Self-supervised Correlation Mining Network (SCM-Net) to rearrange the source images in the feature space. For improving the fidelity of cross-scale pose transformation, we propose a graph based Body Structure Retaining Loss.
  arXiv  Detail & Related papers  (2021-11-26T03:57:46Z)
• Modelling Neighbor Relation in Joint Space-Time Graph for Video Correspondence Learning [53.74240452117145]
  This paper presents a self-supervised method for learning reliable visual correspondence from unlabeled videos. We formulate the correspondence as finding paths in a joint space-time graph, where nodes are grid patches sampled from frames, and are linked by two types of edges. Our learned representation outperforms the state-of-the-art self-supervised methods on a variety of visual tasks.
  arXiv  Detail & Related papers  (2021-09-28T05:40:01Z)

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.