Search Results for author:
Found 3 papers, 2 papers with code
Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification
Experimental results show that this framework can use the data with only image-level labels to improve the generalization of the object detection model.
FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks
Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.
Multi-scale Convolutional Neural Networks for Crowd Counting
Crowd counting on static images is a challenging problem due to scale variations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
