Feature pyramid network with multi-scale prediction fusion for real-time semantic segmentation
T Van Quyen, MY Kim - Neurocomputing, 2023 - Elsevier
Feature pyramid network (FPN) is constructed from a bottom-up pathway and a top-down
pathway. The method involves multi-scale features, so it can obtain rich contextual
information from lower scales and high resolution from the largest scale. Additionally,
different receptive fields are effective to capture both thin and large objects in image scenes.
All feature maps concatenate together to predict the targets. However, the average pooling
method yields the problem of combining the best predictions with poorer ones. In this paper …
pathway. The method involves multi-scale features, so it can obtain rich contextual
information from lower scales and high resolution from the largest scale. Additionally,
different receptive fields are effective to capture both thin and large objects in image scenes.
All feature maps concatenate together to predict the targets. However, the average pooling
method yields the problem of combining the best predictions with poorer ones. In this paper …
Feature Pyramid Network with Multi-Scale Prediction Fusion for Real-Time Semantic Segmentation
MY Kim, TV Quyen - Available at SSRN 4179877 - papers.ssrn.com
Feature pyramid network (FPN) is constructed from a bottom-up pathway and a top-down
pathway. The method involves multi-scale features, so it can obtain rich contextual
information from lower scales and high resolution from the largest scale. Additionally,
different receptive fields are effective to capture both thin and large objects in image scenes.
All feature maps concatenate together to predict the targets. However, the average pooling
method yields the problem of combining the best predictions with poorer ones. In this paper …
pathway. The method involves multi-scale features, so it can obtain rich contextual
information from lower scales and high resolution from the largest scale. Additionally,
different receptive fields are effective to capture both thin and large objects in image scenes.
All feature maps concatenate together to predict the targets. However, the average pooling
method yields the problem of combining the best predictions with poorer ones. In this paper …
이 검색어에 대한 최상의 검색결과 표시 모든 검색결과 표시