4 papers
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Dongting Hu, Jierun Chen, Xijie Huang +16
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…
Elevator, Escalator, or Neither? Classifying Conveyor State Using Smartphone under Arbitrary Pedestrian Behavior
Tianlang He, Zhiqiu Xia, S. -H. Gary Chan
Knowing a pedestrian's conveyor state of ''elevator,'' ''escalator,'' or ''neither'' is fundamental to many applications such as indoor navigation and people flow management. Previ…
StableKD: Breaking Inter-block Optimization Entanglement for Stable Knowledge Distillation
Shiu-hong Kao, Jierun Chen, S. H. Gary Chan
Knowledge distillation (KD) has been recognized as an effective tool to compress and accelerate models. However, current KD approaches generally suffer from an accuracy drop and/or…
Target-agnostic Source-free Domain Adaptation for Regression Tasks
Tianlang He, Zhiqiu Xia, Jierun Chen +2
Unsupervised domain adaptation (UDA) seeks to bridge the domain gap between the target and source using unlabeled target data. Source-free UDA removes the requirement for labeled s…