Year: 2022
Type: dissertation
Abstract: Deep learning has achieved great success in various computer vision tasks.When deploying deep learning models on different devices or a single device at different times, the amount of available resources can be different.Therefore, it is an important research topic to design neural networks that can adapt to various scenarios with different computational resources and achieve a trade-off between accuracy and efficiency.To this end, one branch of existing methods is adaptive inference with sample-wise dynamic architecture.These methods can be grouped into three categories: dynamic routing, dynamic depth, and dynamic width.In this dissertation, we will focus on dynamic post-training quantization (PQ) in the dynamic routing category and early exiting in the dynamic depth category.Existing PQ methods have two problems: (a) require a possibly inaccessible training dataset for model calibration, and (b) are hard to be generalized to low bit-width quantization precision.For early-exiting methods, we find there exists a train-test mismatch problem in prior works that can cause a train-test domain gap.In this dissertation, we will explore how to solve these three problems to improve the generalizability and performance of the dynamic models.Given constrained computational resources, PQ uses a calibration dataset to quantize a trained floating-point neural network to an efficient quantized one.The calibration dataset is usually sampled from training data.However, training data may not be available because of its large storage requirement or confidential issues when the model is being quantized.In the first part of this dissertation, we propose a cross-domain calibration method that uses out-ofdomain data for calibration when in-domain training data is unavailable so that PQ can be applied more flexibly.PQ works well in the case of relatively high quantization bit-widths.To make the model work in a wider range of bit-widths, we propose Any-Precision Deep Neural Network (APDNN), which is trained with a new Throughout my PhD study, I have received a great deal of support and help.First of all, it was my great honor to work with my advisors Prof.
Author: Yu, Haichao
Institution: University of Illinois Urbana-Champaign
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7220754132