Enhancing deep neural networks through complex-valued representations and Kuramoto synchronization dynamics
This work addresses the challenge of representing multiple objects in visual scenes for deep learning applications, offering a neuroscience-inspired approach that is incremental in nature.
The paper tackled the problem of object binding in deep learning models for visual categorization by integrating complex-valued representations with Kuramoto synchronization dynamics, resulting in improved performance over real-valued and non-synchronized complex-valued models on multi-object image tasks.
Neural synchrony is hypothesized to play a crucial role in how the brain organizes visual scenes into structured representations, enabling the robust encoding of multiple objects within a scene. However, current deep learning models often struggle with object binding, limiting their ability to represent multiple objects effectively. Inspired by neuroscience, we investigate whether synchrony-based mechanisms can enhance object encoding in artificial models trained for visual categorization. Specifically, we combine complex-valued representations with Kuramoto dynamics to promote phase alignment, facilitating the grouping of features belonging to the same object. We evaluate two architectures employing synchrony: a feedforward model and a recurrent model with feedback connections to refine phase synchronization using top-down information. Both models outperform their real-valued counterparts and complex-valued models without Kuramoto synchronization on tasks involving multi-object images, such as overlapping handwritten digits, noisy inputs, and out-of-distribution transformations. Our findings highlight the potential of synchrony-driven mechanisms to enhance deep learning models, improving their performance, robustness, and generalization in complex visual categorization tasks.