Retraining-free Model Quantization via One-Shot Weight-Coupling Learning

arXiv:2401.01543v2 Announce Type: replace
Abstract: Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression. Specifically, in the first stage, all …

arxiv cs.cv free quantization replace retraining type via