Lateralized Learning for Multi-Class Visual Classification Tasks
This addresses robustness issues in computer vision for applications like image classification, though it appears incremental as it builds on lateralized concepts from biology.
The paper tackled the problem of computer vision algorithms lacking robustness against adversarial attacks and noisy data by proposing a lateralized learning approach inspired by vertebrate brains. The novel system outperformed state-of-the-art deep learning methods by 19.05% to 41.02% on normal images and 1.36% to 49.22% on adversarial images in multi-class classification tasks.
The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous manner such that different parts of a ``locality-sensitive hashing table'' are often not connected, meaning higher-order patterns are not discovered. Hence these systems are not robust against noisy, irrelevant, and redundant data, resulting in the wrong prediction being made with high confidence. Conversely, vertebrate brains afford heterogeneous knowledge representation through lateralization, enabling modular learning at different levels of abstraction. This work aims to verify the effectiveness, scalability, and robustness of a lateralized approach to real-world problems that contain noisy, irrelevant, and redundant data. The experimental results of multi-class (200 classes) image classification show that the novel system effectively learns knowledge representation at multiple levels of abstraction making it more robust than other state-of-the-art techniques. Crucially, the novel lateralized system outperformed all the state-of-the-art deep learning-based systems for the classification of normal and adversarial images by 19.05% - 41.02% and 1.36% - 49.22%, respectively. Findings demonstrate the value of heterogeneous and lateralized learning for computer vision applications.