Code of various segmentation networks
Notice: These are networks used for comparative experiments in my paper, and they are codes extracted from Papers with Code or other GitHub repositories, not written by me. Unfortunately, I have forgotten the source repositories of the codes, so I couldn't note down the sources. However, you can refer to the paper title and link using Ctrl+F.
Please refer to "Usage.py" for instructions on usage. Basically, their input shape is (N, 3, H, W) and the shape of network output is (N, num_classes, H, W).
cmunet.py (CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network): https://ieeexplore.ieee.org/abstract/document/10230609
ddrnet.py (Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes): https://ieeexplore.ieee.org/abstract/document/9996293
dpt.py (Vision transformers for dense prediction): https://openaccess.thecvf.com/content/ICCV2021/html/Ranftl_Vision_Transformers_for_Dense_Prediction_ICCV_2021_paper.html
efficient_vit (EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction): https://openaccess.thecvf.com/content/ICCV2023/html/Cai_EfficientViT_Lightweight_Multi-Scale_Attention_for_High-Resolution_Dense_Prediction_ICCV_2023_paper.html
BiseNetV2.py (Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation): https://arxiv.org/pdf/2004.02147
fchardnet.py (Hardnet: A low memory traffic network): https://openaccess.thecvf.com/content_ICCV_2019/papers/Chao_HarDNet_A_Low_Memory_Traffic_Network_ICCV_2019_paper.pdf
GAUNet.py (Medical transformer): Gated axial-attention for medical image segmentation): https://arxiv.org/pdf/2102.10662
HRNet.py (Deep high-resolution representation learning for visual recognition): https://arxiv.org/pdf/1908.07919
lawin (Lawin transformer: Improving semantic segmentation transformer with multi-scale representations via large window attention): https://arxiv.org/pdf/2201.01615
MANet.py (Ma-net: A multi-scale attention network for liver and tumor segmentation): https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9201310
mcinet.py (Mci-net: multi-scale context integrated network for liver ct image segmentation): https://www.sciencedirect.com/science/article/abs/pii/S0045790622003408
mfnet.py (MFNet: Multi-Feature Fusion Network for Real-Time Semantic Segmentation in Road Scenes): https://ieeexplore.ieee.org/abstract/document/9839297
paratranscnn.py (ParaTransCNN: Parallelized TransCNN Encoder for Medical Image Segmentation): https://arxiv.org/abs/2401.15307
saunet.py (Saunet: Shape attentive u-net for interpretable medical image segmentation): https://arxiv.org/pdf/2001.07645
transattunet.py (Transattunet: Multi-level attention- guided u-net with transformer for medical image segmentation): https://arxiv.org/pdf/2107.05274
TransUNet.py (TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation): https://arxiv.org/abs/2102.04306
UCTransNet.py (Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer): https://arxiv.org/abs/2109.04335
setr.py (Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers): https://arxiv.org/abs/2012.15840
segnext (Segnext: Rethinking convolutional attention design for semantic segmentation): https://arxiv.org/abs/2209.08575
subpixelsembedding (Small Lesion Segmentation in Brain MRIs with Subpixel Embedding): https://arxiv.org/abs/2109.08791
sfnet (Semantic flow for fast and accurate scene parsing): https://arxiv.org/abs/2002.10120