H
Hao Li
Researcher at University of Maryland, College Park
Publications - 20
Citations - 4391
Hao Li is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Artificial neural network & Graph (abstract data type). The author has an hindex of 12, co-authored 20 publications receiving 3017 citations. Previous affiliations of Hao Li include Chinese Academy of Sciences & Amazon.com.
Papers
More filters
Posted Content
Pruning Filters for Efficient ConvNets
TL;DR: The authors prune filters from CNNs that are identified as having a small effect on the output accuracy, by removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly.
Proceedings Article
Pruning Filters for Efficient ConvNets
TL;DR: The authors prune filters from CNNs that are identified as having a small effect on the output accuracy, by removing whole filters in the network together with their connecting feature maps, the computation costs are reduced significantly.
Proceedings ArticleDOI
Visualizing the Loss Landscape of Neural Nets
TL;DR: This paper explore the structure of neural loss functions and the effect of loss landscapes on generalization, using a range of visualization methods, and explore how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.
Posted Content
Visualizing the Loss Landscape of Neural Nets
TL;DR: This paper introduces a simple "filter normalization" method that helps to visualize loss function curvature and make meaningful side-by-side comparisons between loss functions, and explores how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers.
Journal ArticleDOI
Multimodal Graph-Based Reranking for Web Image Search
TL;DR: Experimental results demonstrate that the proposed reranking approach is more robust than using each individual modality, and it also performs better than many existing methods.