Real-time semantic segmentation is critical for Advanced Driver-Assistance Systems (ADAS), but deploying deep learning models on resource-constrained hardware remains a challenge. This work presents an efficient pipeline for pothole segmentation using the lightweight PP-LiteSeg model, evaluating and comparing two key optimization techniques: post-training quantization and network pruning. Results demonstrate that 8-bit integer (INT8) quantization is highly effective, achieving a 3.54x speedup in GPU compute time with only a minimal, well-controlled loss in segmentation accuracy. While network pruning also reduces model size and latency, it comes at a more pronounced cost to performance. In conclusion, while quantization offers a superior trade-off between speed and accuracy, network pruning remains a valuable strategy for applications where memory compression is the primary objective.
Building similarity graph...
Analyzing shared references across papers
Loading...
William D'Abruzzo Martins
Fernando Santos Osório
Diego Renan Bruno
Building similarity graph...
Analyzing shared references across papers
Loading...
Martins et al. (Tue,) studied this question.
www.synapsesocial.com/papers/69b4fc1fb39f7826a300cd14 — DOI: https://doi.org/10.22456/2175-2745.150751