?
Efficient Pruning Optimization for Trainable Descriptor-Based Facade Signboard Classification
Commercial facade service classification from streetlevel imagery benefits from multi-branch pipelines that fuse global facade appearance with signboard-centric cues; however, this design increases inference cost and hinders large-scale deployment. We study pruning for a multi-branch facade recognition pipeline with a trainable signboard descriptor and compare unstructured magnitude pruning with structured baselines, including channel pruning and latency-aware structured pruning. We further propose a customized, architecture-aware pruning strategy that allocates sparsity across modules according to their sensitivity and computational profile. Experiments on a curated Google Street View subset and the Signboard Classification Dataset show that unstructured pruning reduces parameters, but yields limited wall-clock speedup, whereas structured pruning provides substantial acceleration. At 50% sparsity, the proposed method reduces latency from 14.3 ms to 7.9 ms and FLOPs from 2.83G to 1.26G while preserving macro-averaged F1-score close to the baseline (0.836 vs. 0.844 on GSV; 0.878 vs. 0.887 on SCD). At 60% sparsity, it further reduces latency to 6.9 ms and FLOPs to 1.04G with competitive performance (0.826 on GSV; 0.868 on SCD). Overall, the proposed strategy improves the accuracy– efficiency trade-off of facade service recognition under realistic domain variability.