18 June 2024 in Information Processing & Management
16 July 2024 in Information Processing & Management
1 October 2026 in IEEE Embedded Systems Letters
Enhancing the efficiency of deep neural networks enables complex computer vision applications, such as semantic segmentation, to meet latency requirements on resource-limited embedded systems. By optimizing network parameters, computation overhead can be reduced, leading to lower inference latency. We present TinySegAdapt, a zero-shot architecture search framework for deploying semantic segmentation networks on the ultra-low-power TinyML device. TinySegAdapt compresses networks through parameter-tuning-based architecture search, achieving 2.75 percentage points higher mIoU and 34.2% lower latency compared with filter pruning method. We perform accuracy measurement using a pretrained network and weight sharing, rather than accuracy proxies, yielding a 1.30 pp mIoU improvement. Moreover, TinySegAdapt accelerates the search process by 81.3% through evaluating models on a subset of the validation set without fine-tuning. TinySegAdapt finds competitive designs in just 36.5 hours to discover a variant that is 2.2× faster network on TinyML hardware with a 1.49 percentage point mIoU drop on the PASCAL VOC 2012 dataset.