Search Results for author:
Found 4 papers, 2 papers with code
MobileNetV4 -- Universal Models for the Mobile Ecosystem
We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices.
Ranked #427 on
Image Classification
on ImageNet
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks
Our analysis reveals that non-quantized elementwise operations which are prevalent in layers such as parameterized activation functions batch normalization and quantization scaling dominate the inference cost of low-precision models.
Data-Free Neural Architecture Search via Recursive Label Calibration
We identify that the NAS task requires the synthesized data (we target at image domain here) with enough semantics, diversity, and a minimal domain gap from the natural images.
Pareto-Optimal Quantized ResNet Is Mostly 4-bit
In this work, we use ResNet as a case study to systematically investigate the effects of quantization on inference compute cost-quality tradeoff curves.
