Bilateral Guided Aggregation Layer is a feature fusion layer for semantic segmentation that aims to enhance mutual connections and fuse different types of feature representation. It was used in the BiSeNet V2 architecture. Specifically, within the BiSeNet implementation, the layer was used to employ the contextual information of the Semantic Branch to guide the feature response of Detail Branch. With different scale guidance, different scale feature representations can be captured, which inherently encodes the multi-scale information.
Source: BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic SegmentationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Edge-computing | 1 | 33.33% |
Real-Time Semantic Segmentation | 1 | 33.33% |
Semantic Segmentation | 1 | 33.33% |
Component | Type |
|
---|---|---|
1x1 Convolution
|
Convolutions | |
Average Pooling
|
Pooling Operations | |
Batch Normalization
|
Normalization | |
Convolution
|
Convolutions | |
Depthwise Convolution
|
Convolutions |