LinSlot: Exploiting Linear Representation hypothesis for unsupervised attribute discovery from slot based object representation
cs.CV, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-09
License: http://creativecommons.org/licenses/by/4.0/
The gist: This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data.
Terminology
Abstract
This paper studies the problem of learning disentangled representations of objects and their attributes from raw, unstructured image data. Slot-based methods have shown considerable success in unsupervised learning of object representations from images. Block-slot attention-based methods extend this framework to attribute representations by assuming a uniform factorization of object representations into attributes, which may be suboptimal and consequently limit the quality of the learned representations. We therefore investigate a framework for jointly discovering object and attribute representations. Our key contribution is leveraging the Linear Representation Hypothesis (LRH), which postulates that composable concepts can be represented as linearly additive subspaces in slot representations. Based on this insight, we propose a probabilistic model connecting images, slots (objects), and blocks (attributes). We present an architecture that leverages block attention to connect attribute representations to slots and incorporates LRH in both object and attribute representation spaces. This architecture effectively optimizes the Evidence Lower Bound (ELBO) of the proposed graphical model. Our experiments demonstrate (i) effective discovery of disentangled object and attribute representations, (ii) empirical evidence for LRH in slot space, and (iii) the ability to perform image editing owing to the disentangled and interpretable nature of the learned representations. Our experiments on multiple datasets demonstrate improvements in DCI scores over state-of-the-art methods.
Sources
- MONet: Unsupervised Scene Decomposition and Representation
- Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
- Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
- Multi-Object Representation Learning with Iterative Variational Inference
- On the Binding Problem in Artificial Neural Networks
- ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation
- Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment
- R-SQAIR: Relational Sequential Attend, Infer, Repeat
- Visual Concepts Tokenization
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models