Knowledge discovery and transfer on limited datasets

Download files
Access & Terms of Use
open access
Embargoed until 2023-11-05
Copyright: Liu, Zhe
Deep learning has achieved great success in many real-world applications, e.g., computer vision and human healthcare. Current deep learning usually relies on large-scale datasets with large amounts of carefully annotated data, however, objects in the real world follow a long-tailed distribution, i.e., a tremendous number of classes have little data and hard to be collected. Besides, new classes keep emerging that collecting, and particularly annotating examples is impossible. The data insufficiency poses a bottleneck in the robustness of deep learning methods. Targeting this challenge, I propose to ease data insufficiency in two general data situations: single dataset and multiple datasets. For a single dataset, I propose to discover extra knowledge to enrich the learnable information for models (i.e., knowledge discovery). For multiple datasets, I propose to transfer generalizable knowledge to enhance the analysis of limited datasets (i.e., knowledge transfer). To discover extra new knowledge in a single dataset, I propose to implement the discovery process in three levels. 1) Dataset level. Using contrastive relationships as new information to improve data efficiency on small-scale datasets. 2) Subject/class level. Enabling models to be aware about class/subject and thus be robust handling class/subject variance. 3) Instance level. Automating expert analysis as a new supervisor to boost model training. To enable models to transfer knowledge between datasets, I propose to tackle three common transfer problems in the real world. 1) Lacking data in one of the datasets. I transfer cross-domain knowledge from sufficient to insufficient information domains to augment new data and ease data inefficiency. 2) Multi-view aggregation problem. I propose a general multi-view algorithm to transfer and unite different information from hierarchical views. 3) Biased knowledge transfer among datasets. I propose a task-aligned meta-learning model to learn generalizable knowledge for transferring. In this thesis, I have conducted extensive experiments and ablation studies to validate the proposed methods on diverse real-world applications, e.g., limited-scale datasets of human activity recognition, image classification, neural signal analysis, and commercial analysis.
Persistent link to this record
Link to Publisher Version
Link to Open Access Version
Additional Link
Liu, Zhe
Yao, Lina
Conference Proceedings Editor(s)
Other Contributor(s)
Corporate/Industry Contributor(s)
Publication Year
Resource Type
Degree Type
PhD Doctorate
UNSW Faculty
download public version.pdf 7.7 MB Adobe Portable Document Format
Related dataset(s)