7 papers
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
Rui Cao, Yihao Wang, Yuxin Liang +4
Contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. This technique requires a balanced mixture of two ingredients: positive (simi…
ESOD:Edge-based Task Scheduling for Object Detection
Yihao Wang, Ling Gao, Jie Ren +4
Object Detection on the mobile system is a challenge in terms of everything. Nowadays, many object detection models have been designed, and most of them concentrate on precision. H…
Learning to Remove: Towards Isotropic Pre-trained BERT Embedding
Yuxin Liang, Rui Cao, Jie Zheng +2
Pre-trained language models such as BERT have become a more common choice of natural language processing (NLP) tasks. Research in word representation shows that isotropic embedding…
Smart, Adaptive Energy Optimization for Mobile Web Interactions
Jie Ren, Lu Yuan, Petteri Nurmi +6
Web technology underpins many interactive mobile applications. However, energy-efficient mobile web interactions is an outstanding challenge. Given the increasing diversity and com…
Using Machine Learning to Optimize Web Interactions on Heterogeneous Mobile Multi-cores
Lu Yuan, Jie Ren, Ling Gao +2
The web has become a ubiquitous application development platform for mobile systems. Yet, web access on mobile devices remains an energy-hungry activity. Prior work in the field ma…
To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference
Qing Qin, Jie Ren, Jialong Yu +6
The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained…