Preprint
Aug 2026
Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines
This work presents a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization, and generalizes to any detection-classification edge pipeline.
V. Raju
· 0 citations