Efficient Localized Perception for Resource-Constrained Vision Systems

Despite the rapid advancement in the field of image recognition, the processing of high-resolution imagery remains a computational challenge. However, this processing is pivotal for extracting detailed object insights in areas ranging from autonomous vehicle navigation to medical imaging analyses. Our study introduces a framework aimed at mitigating these challenges by leveraging memory efficient patch based processing for high resolution images. It incorporates a global context representation alongside local patch information, enabling a comprehensive understanding of the image content. In contrast to traditional training methods which are limited by memory constraints, our method enables training of ultra high resolution images. We demonstrate the effectiveness of our method through superior performance on 4 different benchmarks across classification, object detection, and segmentation. Notably, the proposed method achieves strong performance even on resource-constrained devices like Jetson Nano. Our code is available at https://shorturl.at/ikVib.