Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation
Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental informa...
Tags：Paper and LLMsSemantic SegmentationPricing Type
- Pricing Type: Free
- Price Range Start($):
GitHub Link
The GitHub link is https://github.com/mvme-hbut/sgacnet
Introduce
Title GitHub Repository Update for SGACNet Spatial-information Guided Adaptive Context-aware Network. Summary This GitHub repository branch is current and synced with the CyunXiong/SGACNetmain repository, which pertains to the development of SGACNet—a network designed for efficient RGB-D semantic segmentation, incorporating spatial information guidance and adaptive context awareness.
Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information.
Content
We provide the weights for our selected ESANet-R34-NBt1D (with ResNet34 NBt1D backbones) on NYUv2, SunRGBD, and Cityscapes. Download and extract the models to ./trained_models. Please navigate to the cloned directory. Note we are using Python 3.7+. Torch 1.3.1 and torchvision 0.4.2 ImageNet can be downloaded for our selected backbones on the above datasets. Stored in <dir>/trained_models/imagenet. Note that some parameters are different in Cityscapes. Evaluation on SUN RGB-D is similar to NYUv2. Yang Zhang, Chenyun Xiong, Junjie Liu, Xuhui Ye, and Guodong Sun. Spatial-information Guided Adaptive Context-aware Network for Efficient RGBD Semantic Segmentation[J]. IEEE Sensors Journal, 2023.
Related
In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.
