首页|Investigators from Department of Computer Sciences and Engineering Report New Da ta on Artificial Intelligence (Semantic Segmentation Based On Enhanced Gated Pyr amid Network With Lightweight Attention Module)
Investigators from Department of Computer Sciences and Engineering Report New Da ta on Artificial Intelligence (Semantic Segmentation Based On Enhanced Gated Pyr amid Network With Lightweight Attention Module)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Artificial Intelligence. According to news reporting originating from Hyderabad, India, by NewsRx correspondents, research stated, "Semantic segmentation has ma de tremendous progress in recent years. The development of large datasets and th e regression of convolutional models have enabled effective training of very lar ge semantic model." Our news editors obtained a quote from the research from the Department of Compu ter Sciences and Engineering, "Nevertheless, higher capacity indicates a higher computational problem, thus preventing realtime operation. Yet, due to the limi ted annotations, the models may have relied heavily on the available contexts in the training data, resulting in poor generalization to previously unseen scenes . Therefore, to resolve these issues, Enhanced Gated Pyramid network (GPNet) wit h Lightweight Attention Module (LAM) is proposed in this paper. GPNet is used fo r semantic feature extraction and GPNet is enhanced by the pre-trained dilated D etNet and Dense Connection Block (DCB). LAM approach is applied to habitually re scale the different feature channels weights. LAM module can increase the accura cy and effectiveness of the proposed methodology. The performance of proposed me thod is validated using Google Colab environment with different datasets such as Cityscapes, CamVid and ADE20K. The experimental results are compared with vario us methods like GPNet-ResNet-101 and GPNet-ResNet-50 in terms of IoU, precision, accuracy, F1 score and recall."
HyderabadIndiaAsiaArtificial Intel ligenceDepartment of Computer Sciences and Engineering
NETL
NSTL
