Bag of tricks for building an accurate and slim object detector for embedded applications

[PDF] arxiv.org

Budget-Aware Pruning: Handling Multiple Domains with Less Parameters

SF Santos, R Berriel, T Oliveira-Santos, N Sebe… - arXiv preprint arXiv …, 2023 - arxiv.org
Deep learning has achieved state-of-the-art performance on several computer vision tasks
and domains. Nevertheless, it still has a high computational cost and demands a significant …
相关文章
[PDF] arxiv.org

Soft-labeling Strategies for Rapid Sub-Typing

G Rosario, D Noever, M Ciolino - arXiv preprint arXiv:2209.12684, 2022 - arxiv.org
The challenge of labeling large example datasets for computer vision continues to limit the
availability and scope of image repositories. This research provides a new method for …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Budget-Aware Pruning for Multi-Domain Learning

SF Santos, R Berriel, T Oliveira-Santos, N Sebe… - arXiv preprint arXiv …, 2022 - arxiv.org
Deep learning has achieved state-of-the-art performance on several computer vision tasks
and domains. Nevertheless, it still has a high computational cost and demands a significant …
相关文章

Budget-Aware Pruning for Multi-domain Learning

SF dos Santos, R Berriel, T Oliveira-Santos… - … Conference on Image …, 2023 - Springer
Deep learning has achieved state-of-the-art performance on several computer vision tasks
and domains. Nevertheless, it still has a high computational cost and demands a significant …
相关文章 所有 4 个版本