Equivariant Unsupervised Object Detection with Learnable Riesz Transform and Composite Spatial Transformers
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Building models robust to transformations such as rotation, scale, and translation is a challenge in machine learning and computer vision. Existing approaches often provide only partial and discrete equivariance (group equivariance) or rely on supervision or very abundant data to learn equivariant representations. To achieve fine-grained equivariance from low data, we combine and improve over both approaches. We propose a novel, learnable, Riesz-transform-based architecture that achieves built-in group equivariance for translation, rotation, and scale. We combine it with a Spatial Transform Network (STN) tailored for the sequential estimation of composite transformations, reducing the combinatorial data requirements for learning fine-grained equivariance. Improved generalization guarantees and extensive experiments demonstrate that our approach brings improvements over state-of-the-art methods in unsupervised representation learning and object discovery, even more so in low-data regimes.
Fields of Study & Subjects
Advanced Neural Network Applications
Advanced Image and Video Retrieval Techniques
Domain Adaptation and Few-Shot Learning
Publication details
- Journal / source
- HAL
- Publication date
- 3 June 2026
- Language
- EN