Self notes
Research
- Methodology::
- Key Constructs::
- IVs::
- DVs::
- Moderators::
- Others::
- Key_Findings::
- Contributions::
- Limitations::
Self Critique
- Critique
- Pros
- Cons
- How is it relevant to my research?
- Relevant_topic::
- Use::
How to create a โSelf Notesโ
Cite
Wang, Chien-Yao, Hong-Yuan Mark Liao, I.-Hau Yeh, Yueh-Hua Wu, Ping-Yang Chen, and Jun-Wei Hsieh. โCSPNet: A New Backbone That Can Enhance Learning Capability of CNN.โ arXiv, November 26, 2019. http://arxiv.org/abs/1911.11929.
Synth
Contribution::
Md
Author:: Wang, Chien-Yao
Author:: Liao, Hong-Yuan Mark
Author:: Yeh, I.-Hau
Author:: Wu, Yueh-Hua
Author:: Chen, Ping-Yang
Author:: Hsieh, Jun-WeiTitle:: CSPNet: A New Backbone that can Enhance Learning Capability of CNN
Year:: 2019
Citekey:: @WangEtAl2019Tags:: Computer Science - Computer Vision and Pattern Recognition
itemType:: preprint
LINK
Abstract
abstract:: Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap devices from appreciating the advanced technology. In this paper, we propose Cross Stage Partial Network (CSPNet) to mitigate the problem that previous works require heavy inference computations from the network architecture perspective. We attribute the problem to the duplicate gradient information within network optimization. The proposed networks respect the variability of the gradients by integrating feature maps from the beginning and the end of a network stage, which, in our experiments, reduces computations by 20% with equivalent or even superior accuracy on the ImageNet dataset, and significantly outperforms state-of-the-art approaches in terms of AP50 on the MS COCO object detection dataset. The CSPNet is easy to implement and general enough to cope with architectures based on ResNet, ResNeXt, and DenseNet. Source code is at https://github.com/WongKinYiu/CrossStagePartialNetworks.
Annotations
Image
Image
Highlight
Figure 1: Proposed CSPNet can be applied on ResNet [7], ResNeXt [39], DenseNet [11], etc. It not only reduce computation cost and memory usage of these networks, but also benefit on inference speed and accuracy. (Go to Paper)
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Highlight
Figure 3: Different kind of feature fusion strategies. (a) single path DenseNet, (b) proposed CSPDenseNet: transition โ concatenation โ transition, (c) concatenation โ transition, and (d) transition โ concatenation. (Go to Paper)
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
Image
