Semantic segmentation
See:
- AI/Deep learning/Encoder-decoder networks for image segmentation
- AI/Computer Vision/Object detection
# Resources
- https://en.wikipedia.org/wiki/Image_segmentation
- https://github.com/mrgloom/awesome-semantic-segmentation
- https://blog.athelas.com/a-brief-history-of-cnns-in-image-segmentation-from-r-cnn-to-mask-r-cnn-34ea83205de4
- Overview of semantic image segmentation
# Code
- #CODE
DeepLab2
- DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
- #CODE Segmentation models with pretrained backbones (PyTorch)
- #CODE
https://github.com/qubvel/segmentation_models
- Python library with Neural Networks for Image Segmentation based on Keras and TensorFlow
- #CODE https://www.tensorflow.org/tutorials/images/segmentation
- #CODE https://github.com/yassouali/pytorch-segmentation
# References
- #PAPER Fully Convolutional Networks for Semantic Segmentation (Long 2015)
- #PAPER
CGNet: A Light-weight Context Guided Network for Semantic Segmentation (Wu 2018)
- Context Guided (CG) block learns the joint feature of both local feature and surrounding context, and further improves the joint feature with the global context
- CGNet captures contextual information in all stages of the network and is specially tailored for increasing segmentation accuracy
- CGNet is also elaborately designed to reduce the number of parameters and save memory footprint
- #PAPER #REVIEW Deep learning for cardiac image segmentation: A review (2019)
- #PAPER Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (Cheng 2020)
- #PAPER Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (Wang 2020)
- #PAPER #REVIEW Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey (Sultana, 2020)
- #PAPER Towards infield, live plant phenotyping using a reduced-parameter CNN (Atanbori 2020)
- #PAPER Learning What Not to Segment: A New Perspective on Few-Shot Segmentation (Lang 2022)
- #PAPER
k-means Mask Transformer (Yu 2022)
- #CODE https://github.com/google-research/deeplab2
- rethought the relationship between pixels and object queries and propose to reformulate the cross-attention learning as a clustering process
- k-means Mask Xformer (kMaX-DeepLab) for segmentation tasks is inspired by the traditional k-means clustering algorithm