DKT: A First Look at Dynamic Kernel Tuning for Pedestrian Attribute Recognition

In this work, we propose Dynamic Kernel Tuning (DKT), which dynamically selects a subset of kernels per attribute for the pedestrian attribute recognition problem. By tuning kernels for each attribute class in real time, DKT optimizes both training and inference times. Experimental evaluation of DKT on the Market-1501S dataset achieves a reduction in training time from 234 seconds to 32.5 seconds and a reduction in inference time from 35 ms to 2.3 ms, without impacting accuracy. Additionally, we benchmark model quantization methods and establish theoretical results to foster future research in dynamic kernel tuning.