share
Location-aware-Upsampling-for-Semantic-Segmentation
The Pytorch implementation of "Location-aware Upsampling for Semantic Segmentation" (LaU)
view repo
Location-aware Upsampling for Semantic Segmentation
Many successful learning targets such as dice loss and cross-entropy loss have enabled unprecedented breakthroughs in segmentation tasks. Beyond semantic supervision, this paper aims to introduce location prediction into semantic segmentation from a new viewpoint: let pixels determine their own coordinates. Based on this idea, we present a Location-aware Upsampling (LaU) that adaptively refines the interpolating coordinates with trainable offsets. Then, location-aware losses are established by encouraging pixels to move towards well-classified locations. An LaU is offset prediction coupled with interpolation, which is trained end-to-end to generate confidence score at each position from coarse to fine. Guided by location-aware losses, the new module can replace its plain counterpart e.g., bilinear upsampling in a plug-and-play manner to further boost the leading encoder-decoder approaches. Extensive experiments validate the consistent improvement over the state-of-the-art methods on benchmark datasets. Our code is available at https://github.com/HolmesShuan/Location-aware-Upsampling-for-Semantic-Segmentation
READ FULL TEXT