Neuromorphic Visual Scene Understanding with Resonator Networks
arXiv:2208.12880 · doi:10.1038/s42256-024-00848-0
Abstract
Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference procedure, involving a combinatorial search across object identities and poses. Here we propose a neuromorphic solution exploiting three key concepts: (1) a computational framework based on Vector Symbolic Architectures (VSA) with complex-valued vectors; (2) the design of Hierarchical Resonator Networks (HRN) to factorize the non-commutative transforms translation and rotation in visual scenes; (3) the design of a multi-compartment spiking phasor neuron model for implementing complex-valued resonator networks on neuromorphic hardware. The VSA framework uses vector binding operations to form a generative image model in which binding acts as the equivariant operation for geometric transformations. A scene can, therefore, be described as a sum of vector products, which can then be efficiently factorized by a resonator network to infer objects and their poses. The HRN features a partitioned architecture in which vector binding is equivariant for horizontal and vertical translation within one partition and for rotation and scaling within the other partition. The spiking neuron model allows mapping the resonator network onto efficient and low-power neuromorphic hardware. Our approach is demonstrated on synthetic scenes composed of simple 2D shapes undergoing rigid geometric transformations and color changes. A companion paper demonstrates the same approach in real-world application scenarios for machine vision and robotics.
23 pages, 8 figures, minor revisions and extended supplementary material
References in corpus (14)
- Event-based Vision: A Survey
- Shortcut Learning in Deep Neural Networks
- Memory and information processing in neuromorphic systems
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
- A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges
- A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations
- Vector Symbolic Architectures as a Computing Framework for Emerging Hardware
- Assaying Out-Of-Distribution Generalization in Transfer Learning
- Neural Manifold Clustering and Embedding
- Visual Odometry with Neuromorphic Resonator Networks
- Beta-VAE Reproducibility: Challenges and Extensions
- Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
- Learning and generalization of compositional representations of visual scenes