Enabling Computer Vision Driven Assistive Devices for the Visually Impaired via Micro-architecture Design Exploration
This work addresses the problem of high computational costs and privacy concerns for visually impaired users by enabling on-device AI assistants, though it is incremental as it builds upon existing MobileNetV2-SSD methods.
The study tackled the challenge of deploying efficient object detection for assistive devices for the visually impaired by optimizing the micro-architecture of a MobileNetV2-SSD network, resulting in a compact deep neural network with a balanced trade-off between accuracy, size, and speed suitable for on-device operation.
Recent improvements in object detection have shown potential to aid in tasks where previous solutions were not able to achieve. A particular area is assistive devices for individuals with visual impairment. While state-of-the-art deep neural networks have been shown to achieve superior object detection performance, their high computational and memory requirements make them cost prohibitive for on-device operation. Alternatively, cloud-based operation leads to privacy concerns, both not attractive to potential users. To address these challenges, this study investigates creating an efficient object detection network specifically for OLIV, an AI-powered assistant for object localization for the visually impaired, via micro-architecture design exploration. In particular, we formulate the problem of finding an optimal network micro-architecture as an numerical optimization problem, where we find the set of hyperparameters controlling the MobileNetV2-SSD network micro-architecture that maximizes a modified NetScore objective function for the MSCOCO-OLIV dataset of indoor objects. Experimental results show that such a micro-architecture design exploration strategy leads to a compact deep neural network with a balanced trade-off between accuracy, size, and speed, making it well-suited for enabling on-device computer vision driven assistive devices for the visually impaired.