Grouped Discrete Representation Guides Object-Centric Learning
Not on the map. Why?
Abstract (arXiv)
Similar to humans perceiving visual scenes as objects, Object-Centric Learning (OCL) can abstract dense images or videos into sparse object-level features. Transformer-based OCL handles complex textures well due to the decoding guidance of discrete representation, obtained by discretizing noisy features in image or video feature maps using template features from a codebook. However, treating features as minimal units overlooks their composing attributes, thus impeding model generalization; indexing features with natural numbers loses attribute-level commonalities and characteristics, thus diminishing heuristics for model convergence. We propose textitGrouped Discrete Representation (GDR) to address these issues by grouping features into attributes and indexing them with tuple numbers. In extensive experiments across different query initializations, dataset modalities, and model architectures, GDR consistently improves convergence and generalizability. Visualizations show that our method effectively captures attribute-level information in features. The source code will be available upon acceptance.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 1 Jul 2024.
Builds on
24 of 41 references.
References · 24
- 2017Neural Discrete Representation Learningcited by 4,650
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
- 2020Object-Centric Learning with Slot Attentioncited by 865
- 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
- 2021Conditional Object-Centric Learning from Videocited by 247
- 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
- 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
- 2021Illiterate DALL-E Learns to Composecited by 147
- 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
- 2019Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolutioncited by 140
- 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
12 more
- 2017CondenseNet: An Efficient DenseNet using Learned Group Convolutionscited by 121
- 2023Object-Centric Slot Diffusioncited by 90
- 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
- 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
- 2022Improving Object-centric Learning with Query Optimizationcited by 60
- 2018Temporal Difference Variational Auto-Encodercited by 48
- 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
- 2021Learning Object-Centric Representations of Multi-Object Scenes from Multiple Viewscited by 37
- 2022Neural Systematic Bindercited by 37
- 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
- 2023FOCUS: Object-Centric World Models for Robotics Manipulationcited by 17
- 2023Object-centric Learning with Cyclic Walks between Parts and Wholecited by 16
Built on by
Citing papers per year: 2024: 2.
2 papers.