One-Shot Aggregation with an Identity Mapping and eSE is an image model block that extends one-shot aggregation with a residual connection and effective squeeze-and-excitation block. It is proposed as part of the VoVNetV2 CNN architecture.
The module adds an identity mapping to the OSA module - the input path is connected to the end of an OSA module that is able to backpropagate the gradients of every OSA module in an end-to-end manner on each stage like a ResNet. Additionally, a channel attention module - effective Squeeze-Excitation - is used which is like regular squeeze-and-excitation but uses only one FC layer with $C$ channels instead of two FCs without a channel dimension reduction, which maintains channel information.
Source: CenterMask : Real-Time Anchor-Free Instance SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Instance Segmentation | 1 | 14.29% |
Object Detection | 1 | 14.29% |
Panoptic Segmentation | 1 | 14.29% |
Real-time Instance Segmentation | 1 | 14.29% |
Real-Time Object Detection | 1 | 14.29% |
Semantic Segmentation | 1 | 14.29% |
Semi-Supervised Instance Segmentation | 1 | 14.29% |