A Strided EESP unit is based on the EESP Unit but is modified to learn representations more efficiently at multiple scales. Depth-wise dilated convolutions are given strides, an average pooling operation is added instead of an identity connection, and the element-wise addition operation is replaced with a concatenation operation, which helps in expanding the dimensions of feature maps efficiently.
Source: ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural NetworkPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
General Classification | 1 | 14.29% |
Image Classification | 1 | 14.29% |
Language Modelling | 1 | 14.29% |
Object Detection | 1 | 14.29% |
Real-Time Object Detection | 1 | 14.29% |
Real-Time Semantic Segmentation | 1 | 14.29% |
Semantic Segmentation | 1 | 14.29% |