Gao Huang, Zhuang Liu, Laurens Van Der Maaten, & Kilian Q. Weinberger (2017)
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2261-2269.
DOI: https://doi.org/10.1109/cvpr.2017.243
Abstract. Introduces DenseNet, in which each layer receives the concatenated feature maps of all preceding layers within a dense block, maximising feature reuse and gradient flow with fewer parameters than equivalent ResNets.
Tags: cnn densenet