Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387149600> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4387149600 abstract "In computer vision, object detection is an important task. Whether it is a single-stage or two-stage method, it has been based on anchor-based detectors for several years. In recent years, due to multi-scale feature fusion and Focal Loss, anchor-free detectors have become popular. However, both anchor-based and anchor-free detectors have the problems of large computation, poor stability, many hyperparameters, and imbalance between positive and negative samples. This paper proposes a one-stage target detection network (AMBNet) that automatically matches ground truth boxes, avoid manual selection of anchors, which is difficult to match multi-scale targets. The size of the grid can be adjusted according to the size of the detection target. It is still regressing the target from rectangles that are closer to the ground-truth boxes, so the training is more stable. By calculation, when the number of grids is 64, no concentric rectangles are set, and the average IOU is 0.7753. When setting 4 concentric rectangles, the average value of IOU is 0.8211." @default.
- W4387149600 created "2023-09-29" @default.
- W4387149600 creator A5049482829 @default.
- W4387149600 creator A5049876086 @default.
- W4387149600 creator A5055267677 @default.
- W4387149600 creator A5090889288 @default.
- W4387149600 date "2023-08-11" @default.
- W4387149600 modified "2023-10-18" @default.
- W4387149600 title "AMB:Automatically Matches Boxes Module for One-Stage Object Detection" @default.
- W4387149600 cites W2302255633 @default.
- W4387149600 cites W2412782625 @default.
- W4387149600 cites W2565639579 @default.
- W4387149600 cites W2570343428 @default.
- W4387149600 cites W2618530766 @default.
- W4387149600 cites W2963037989 @default.
- W4387149600 cites W2963113370 @default.
- W4387149600 cites W2982770724 @default.
- W4387149600 cites W3012573144 @default.
- W4387149600 cites W3035396860 @default.
- W4387149600 cites W639708223 @default.
- W4387149600 doi "https://doi.org/10.1109/icipca59209.2023.10257868" @default.
- W4387149600 hasPublicationYear "2023" @default.
- W4387149600 type Work @default.
- W4387149600 citedByCount "0" @default.
- W4387149600 crossrefType "proceedings-article" @default.
- W4387149600 hasAuthorship W4387149600A5049482829 @default.
- W4387149600 hasAuthorship W4387149600A5049876086 @default.
- W4387149600 hasAuthorship W4387149600A5055267677 @default.
- W4387149600 hasAuthorship W4387149600A5090889288 @default.
- W4387149600 hasConcept C112972136 @default.
- W4387149600 hasConcept C11413529 @default.
- W4387149600 hasConcept C119857082 @default.
- W4387149600 hasConcept C127413603 @default.
- W4387149600 hasConcept C146849305 @default.
- W4387149600 hasConcept C153180895 @default.
- W4387149600 hasConcept C154945302 @default.
- W4387149600 hasConcept C177264268 @default.
- W4387149600 hasConcept C187691185 @default.
- W4387149600 hasConcept C199360897 @default.
- W4387149600 hasConcept C201995342 @default.
- W4387149600 hasConcept C2524010 @default.
- W4387149600 hasConcept C2776151529 @default.
- W4387149600 hasConcept C2780451532 @default.
- W4387149600 hasConcept C2781238097 @default.
- W4387149600 hasConcept C31972630 @default.
- W4387149600 hasConcept C33923547 @default.
- W4387149600 hasConcept C41008148 @default.
- W4387149600 hasConcept C45374587 @default.
- W4387149600 hasConcept C76155785 @default.
- W4387149600 hasConcept C8642999 @default.
- W4387149600 hasConcept C94915269 @default.
- W4387149600 hasConceptScore W4387149600C112972136 @default.
- W4387149600 hasConceptScore W4387149600C11413529 @default.
- W4387149600 hasConceptScore W4387149600C119857082 @default.
- W4387149600 hasConceptScore W4387149600C127413603 @default.
- W4387149600 hasConceptScore W4387149600C146849305 @default.
- W4387149600 hasConceptScore W4387149600C153180895 @default.
- W4387149600 hasConceptScore W4387149600C154945302 @default.
- W4387149600 hasConceptScore W4387149600C177264268 @default.
- W4387149600 hasConceptScore W4387149600C187691185 @default.
- W4387149600 hasConceptScore W4387149600C199360897 @default.
- W4387149600 hasConceptScore W4387149600C201995342 @default.
- W4387149600 hasConceptScore W4387149600C2524010 @default.
- W4387149600 hasConceptScore W4387149600C2776151529 @default.
- W4387149600 hasConceptScore W4387149600C2780451532 @default.
- W4387149600 hasConceptScore W4387149600C2781238097 @default.
- W4387149600 hasConceptScore W4387149600C31972630 @default.
- W4387149600 hasConceptScore W4387149600C33923547 @default.
- W4387149600 hasConceptScore W4387149600C41008148 @default.
- W4387149600 hasConceptScore W4387149600C45374587 @default.
- W4387149600 hasConceptScore W4387149600C76155785 @default.
- W4387149600 hasConceptScore W4387149600C8642999 @default.
- W4387149600 hasConceptScore W4387149600C94915269 @default.
- W4387149600 hasLocation W43871496001 @default.
- W4387149600 hasOpenAccess W4387149600 @default.
- W4387149600 hasPrimaryLocation W43871496001 @default.
- W4387149600 hasRelatedWork W1837097281 @default.
- W4387149600 hasRelatedWork W1966410754 @default.
- W4387149600 hasRelatedWork W1988485990 @default.
- W4387149600 hasRelatedWork W2007544051 @default.
- W4387149600 hasRelatedWork W2095705906 @default.
- W4387149600 hasRelatedWork W2334336442 @default.
- W4387149600 hasRelatedWork W2732308154 @default.
- W4387149600 hasRelatedWork W2922421953 @default.
- W4387149600 hasRelatedWork W2975200075 @default.
- W4387149600 hasRelatedWork W3177406559 @default.
- W4387149600 isParatext "false" @default.
- W4387149600 isRetracted "false" @default.
- W4387149600 workType "article" @default.