Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385260944> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4385260944 abstract "We present a conceptually simple, efficient, and general framework for localization problems in DETR-like models. We add plugins to well-trained models instead of inefficiently designing new models and training them from scratch. The method, called RefineBox, refines the outputs of DETR-like detectors by lightweight refinement networks. RefineBox is easy to implement and train as it only leverages the features and predicted boxes from the well-trained detection models. Our method is also efficient as we freeze the trained detectors during training. In addition, we can easily generalize RefineBox to various trained detection models without any modification. We conduct experiments on COCO and LVIS $1.0$. Experimental results indicate the effectiveness of our RefineBox for DETR and its representative variants (Figure 1). For example, the performance gains for DETR, Conditinal-DETR, DAB-DETR, and DN-DETR are 2.4 AP, 2.5 AP, 1.9 AP, and 1.6 AP, respectively. We hope our work will bring the attention of the detection community to the localization bottleneck of current DETR-like models and highlight the potential of the RefineBox framework. Code and models will be publicly available at: href{https://github.com/YiqunChen1999/RefineBox}{https://github.com/YiqunChen1999/RefineBox}." @default.
- W4385260944 created "2023-07-26" @default.
- W4385260944 creator A5002942097 @default.
- W4385260944 creator A5010085734 @default.
- W4385260944 creator A5036521568 @default.
- W4385260944 creator A5039059630 @default.
- W4385260944 creator A5073212256 @default.
- W4385260944 creator A5075880303 @default.
- W4385260944 date "2023-07-21" @default.
- W4385260944 modified "2023-09-25" @default.
- W4385260944 title "Enhancing Your Trained DETRs with Box Refinement" @default.
- W4385260944 doi "https://doi.org/10.48550/arxiv.2307.11828" @default.
- W4385260944 hasPublicationYear "2023" @default.
- W4385260944 type Work @default.
- W4385260944 citedByCount "0" @default.
- W4385260944 crossrefType "posted-content" @default.
- W4385260944 hasAuthorship W4385260944A5002942097 @default.
- W4385260944 hasAuthorship W4385260944A5010085734 @default.
- W4385260944 hasAuthorship W4385260944A5036521568 @default.
- W4385260944 hasAuthorship W4385260944A5039059630 @default.
- W4385260944 hasAuthorship W4385260944A5073212256 @default.
- W4385260944 hasAuthorship W4385260944A5075880303 @default.
- W4385260944 hasBestOaLocation W43852609441 @default.
- W4385260944 hasConcept C119857082 @default.
- W4385260944 hasConcept C124101348 @default.
- W4385260944 hasConcept C127413603 @default.
- W4385260944 hasConcept C146978453 @default.
- W4385260944 hasConcept C149635348 @default.
- W4385260944 hasConcept C154945302 @default.
- W4385260944 hasConcept C177264268 @default.
- W4385260944 hasConcept C199360897 @default.
- W4385260944 hasConcept C2776760102 @default.
- W4385260944 hasConcept C2780513914 @default.
- W4385260944 hasConcept C41008148 @default.
- W4385260944 hasConcept C64543145 @default.
- W4385260944 hasConceptScore W4385260944C119857082 @default.
- W4385260944 hasConceptScore W4385260944C124101348 @default.
- W4385260944 hasConceptScore W4385260944C127413603 @default.
- W4385260944 hasConceptScore W4385260944C146978453 @default.
- W4385260944 hasConceptScore W4385260944C149635348 @default.
- W4385260944 hasConceptScore W4385260944C154945302 @default.
- W4385260944 hasConceptScore W4385260944C177264268 @default.
- W4385260944 hasConceptScore W4385260944C199360897 @default.
- W4385260944 hasConceptScore W4385260944C2776760102 @default.
- W4385260944 hasConceptScore W4385260944C2780513914 @default.
- W4385260944 hasConceptScore W4385260944C41008148 @default.
- W4385260944 hasConceptScore W4385260944C64543145 @default.
- W4385260944 hasLocation W43852609441 @default.
- W4385260944 hasOpenAccess W4385260944 @default.
- W4385260944 hasPrimaryLocation W43852609441 @default.
- W4385260944 hasRelatedWork W2087937280 @default.
- W4385260944 hasRelatedWork W2353647904 @default.
- W4385260944 hasRelatedWork W2354251581 @default.
- W4385260944 hasRelatedWork W2357461155 @default.
- W4385260944 hasRelatedWork W2384129116 @default.
- W4385260944 hasRelatedWork W2961085424 @default.
- W4385260944 hasRelatedWork W3145924829 @default.
- W4385260944 hasRelatedWork W3152267458 @default.
- W4385260944 hasRelatedWork W4306674287 @default.
- W4385260944 hasRelatedWork W4312635023 @default.
- W4385260944 isParatext "false" @default.
- W4385260944 isRetracted "false" @default.
- W4385260944 workType "article" @default.