Search Results for author:
Found 4 papers, 1 papers with code
Skipped Feature Pyramid Network with Grid Anchor for Object Detection
In our method, the lower-level feature only connects with the feature at the highest level, making it more reasonable that each level is responsible for detecting objects with fixed scales.
Image Compressed Sensing with Multi-scale Dilated Convolutional Neural Network
During the measurement period, we directly obtain all measurements from a trained measurement network, which employs fully convolutional structures and is jointly trained with the reconstruction network from the input image.
Abs-CAM: A Gradient Optimization Interpretable Approach for Explanation of Convolutional Neural Networks
However, when this method uses backpropagation to obtain gradients, it will cause noise in the saliency map, and even locate features that are irrelevant to decisions.
Obstacles to Constructing de Sitter Space in String Theory
While arguably there have been some successes, this has proven challenging, leading to the de Sitter swampland conjecture: quantum theories of gravity do not admit stable or metastable de Sitter space.
High Energy Physics - Theory High Energy Physics - Phenomenology
