Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319071252> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4319071252 abstract "In target detection, small target detection is always a thorny problem, because there is little pixel information of small target in a picture. However, in the feature extraction phase of most target detection network architectures, the deep feature maps lack information on the edge or geometric details of small targets. Although the shallow feature map is rich in geometric details, it lacks the semantic features of small objects. To solve the above problems, this paper proposes a small target detection model F-SRAF, which combines feature enhancement and attention mechanism. Specifically, firstly, the feature enhancement module is used to extract credible geometric details by combining the shallow high-resolution features with the deep super-resolution semantic features. Then, the channel attention mechanism is added to the deep super-resolution semantic features to enhance the features useful to the target and suppress the background features. Finally, the related detail feature map learned by the network is fused with the semantic feature map added with the channel attention mechanism to output a high-resolution feature map with semantic information. In the experiment of this paper, our method has achieved good results on MS COCO dataset and Tsinghua-Tencent 100K dataset. At the same time, it is proved that this detection algorithm can enhance the semantic information of shallow feature map and has a good detection effect for small targets." @default.
- W4319071252 created "2023-02-04" @default.
- W4319071252 creator A5006782694 @default.
- W4319071252 creator A5030633188 @default.
- W4319071252 creator A5049421884 @default.
- W4319071252 date "2023-02-03" @default.
- W4319071252 modified "2023-09-27" @default.
- W4319071252 title "F-SRAF: a small target detection method based on attention mechanism and feature enhancement" @default.
- W4319071252 doi "https://doi.org/10.1117/12.2660009" @default.
- W4319071252 hasPublicationYear "2023" @default.
- W4319071252 type Work @default.
- W4319071252 citedByCount "0" @default.
- W4319071252 crossrefType "proceedings-article" @default.
- W4319071252 hasAuthorship W4319071252A5006782694 @default.
- W4319071252 hasAuthorship W4319071252A5030633188 @default.
- W4319071252 hasAuthorship W4319071252A5049421884 @default.
- W4319071252 hasConcept C127162648 @default.
- W4319071252 hasConcept C138885662 @default.
- W4319071252 hasConcept C153180895 @default.
- W4319071252 hasConcept C154945302 @default.
- W4319071252 hasConcept C160633673 @default.
- W4319071252 hasConcept C2776151529 @default.
- W4319071252 hasConcept C2776401178 @default.
- W4319071252 hasConcept C2781122975 @default.
- W4319071252 hasConcept C31258907 @default.
- W4319071252 hasConcept C41008148 @default.
- W4319071252 hasConcept C41895202 @default.
- W4319071252 hasConcept C52622490 @default.
- W4319071252 hasConceptScore W4319071252C127162648 @default.
- W4319071252 hasConceptScore W4319071252C138885662 @default.
- W4319071252 hasConceptScore W4319071252C153180895 @default.
- W4319071252 hasConceptScore W4319071252C154945302 @default.
- W4319071252 hasConceptScore W4319071252C160633673 @default.
- W4319071252 hasConceptScore W4319071252C2776151529 @default.
- W4319071252 hasConceptScore W4319071252C2776401178 @default.
- W4319071252 hasConceptScore W4319071252C2781122975 @default.
- W4319071252 hasConceptScore W4319071252C31258907 @default.
- W4319071252 hasConceptScore W4319071252C41008148 @default.
- W4319071252 hasConceptScore W4319071252C41895202 @default.
- W4319071252 hasConceptScore W4319071252C52622490 @default.
- W4319071252 hasLocation W43190712521 @default.
- W4319071252 hasOpenAccess W4319071252 @default.
- W4319071252 hasPrimaryLocation W43190712521 @default.
- W4319071252 hasRelatedWork W2016461833 @default.
- W4319071252 hasRelatedWork W2059299633 @default.
- W4319071252 hasRelatedWork W2084511825 @default.
- W4319071252 hasRelatedWork W2090093270 @default.
- W4319071252 hasRelatedWork W2136485282 @default.
- W4319071252 hasRelatedWork W2382607599 @default.
- W4319071252 hasRelatedWork W2546871836 @default.
- W4319071252 hasRelatedWork W2811390910 @default.
- W4319071252 hasRelatedWork W3197541072 @default.
- W4319071252 hasRelatedWork W4295357754 @default.
- W4319071252 isParatext "false" @default.
- W4319071252 isRetracted "false" @default.
- W4319071252 workType "article" @default.