Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386847536> ?p ?o ?g. }
- W4386847536 abstract "Abstract Semi-supervised learning offers a solution to the high cost and limited availability of manually labeled samples in supervised learning. In semi-supervised visual object detection, the use of unlabeled data can significantly enhance the performance of deep learning models. In this paper, we introduce an end-to-end framework, named CISO (Co-Iteration Semi-Supervised Learning for Object Detection), which integrates a knowledge distillation approach and a collaborative, iterative semi-supervised learning strategy. To maximize the utilization of pseudo-label data and address the scarcity of pseudo-label data due to high threshold settings, we propose a mean iteration approach where all unlabeled data is applied to each training iteration. Pseudo-label data with high confidence is extracted based on an ever-changing threshold (average intersection over union of all pseudo-labeled data). This strategy not only ensures the accuracy of the pseudo-label but also optimizes the use of unlabeled data. Subsequently, we apply a weak-strong data augmentation strategy to update the model. Lastly, we evaluate CISO using Swin Transformer model and conduct comprehensive experiments on MS-COCO. Our framework showcases impressive results, outperforms the state-of-the-art methods by 2.16 mAP and 1.54 mAP with 10% and 5% labeled data, respectively." @default.
- W4386847536 created "2023-09-20" @default.
- W4386847536 creator A5042399868 @default.
- W4386847536 creator A5062285582 @default.
- W4386847536 creator A5064286235 @default.
- W4386847536 date "2023-09-19" @default.
- W4386847536 modified "2023-09-27" @default.
- W4386847536 title "CISO: Co-iteration semi-supervised learning for visual object detection" @default.
- W4386847536 cites W1536680647 @default.
- W4386847536 cites W1608462934 @default.
- W4386847536 cites W1861492603 @default.
- W4386847536 cites W2031489346 @default.
- W4386847536 cites W2156163116 @default.
- W4386847536 cites W2618530766 @default.
- W4386847536 cites W2739879705 @default.
- W4386847536 cites W2884367402 @default.
- W4386847536 cites W2886934227 @default.
- W4386847536 cites W2919115771 @default.
- W4386847536 cites W2963037989 @default.
- W4386847536 cites W2963140444 @default.
- W4386847536 cites W2963150697 @default.
- W4386847536 cites W2963495494 @default.
- W4386847536 cites W2963516811 @default.
- W4386847536 cites W2963930099 @default.
- W4386847536 cites W2979805229 @default.
- W4386847536 cites W2981952041 @default.
- W4386847536 cites W2982157312 @default.
- W4386847536 cites W2982770724 @default.
- W4386847536 cites W2992308087 @default.
- W4386847536 cites W3001083904 @default.
- W4386847536 cites W3035160371 @default.
- W4386847536 cites W3091002423 @default.
- W4386847536 cites W3096609285 @default.
- W4386847536 cites W3098090606 @default.
- W4386847536 cites W3106250896 @default.
- W4386847536 cites W3133744637 @default.
- W4386847536 cites W3138516171 @default.
- W4386847536 cites W3155739706 @default.
- W4386847536 cites W3158661000 @default.
- W4386847536 cites W3169575272 @default.
- W4386847536 cites W3172507542 @default.
- W4386847536 cites W3176709420 @default.
- W4386847536 cites W3176748778 @default.
- W4386847536 cites W3178291178 @default.
- W4386847536 cites W3203810176 @default.
- W4386847536 cites W4312421335 @default.
- W4386847536 cites W4312439170 @default.
- W4386847536 cites W4312605608 @default.
- W4386847536 cites W4312769060 @default.
- W4386847536 cites W4386076325 @default.
- W4386847536 doi "https://doi.org/10.1007/s11042-023-16915-4" @default.
- W4386847536 hasPublicationYear "2023" @default.
- W4386847536 type Work @default.
- W4386847536 citedByCount "0" @default.
- W4386847536 crossrefType "journal-article" @default.
- W4386847536 hasAuthorship W4386847536A5042399868 @default.
- W4386847536 hasAuthorship W4386847536A5062285582 @default.
- W4386847536 hasAuthorship W4386847536A5064286235 @default.
- W4386847536 hasBestOaLocation W43868475361 @default.
- W4386847536 hasConcept C119857082 @default.
- W4386847536 hasConcept C127413603 @default.
- W4386847536 hasConcept C136389625 @default.
- W4386847536 hasConcept C146978453 @default.
- W4386847536 hasConcept C153180895 @default.
- W4386847536 hasConcept C154945302 @default.
- W4386847536 hasConcept C2776145971 @default.
- W4386847536 hasConcept C2776151529 @default.
- W4386847536 hasConcept C2781238097 @default.
- W4386847536 hasConcept C41008148 @default.
- W4386847536 hasConcept C50644808 @default.
- W4386847536 hasConcept C58973888 @default.
- W4386847536 hasConcept C64543145 @default.
- W4386847536 hasConceptScore W4386847536C119857082 @default.
- W4386847536 hasConceptScore W4386847536C127413603 @default.
- W4386847536 hasConceptScore W4386847536C136389625 @default.
- W4386847536 hasConceptScore W4386847536C146978453 @default.
- W4386847536 hasConceptScore W4386847536C153180895 @default.
- W4386847536 hasConceptScore W4386847536C154945302 @default.
- W4386847536 hasConceptScore W4386847536C2776145971 @default.
- W4386847536 hasConceptScore W4386847536C2776151529 @default.
- W4386847536 hasConceptScore W4386847536C2781238097 @default.
- W4386847536 hasConceptScore W4386847536C41008148 @default.
- W4386847536 hasConceptScore W4386847536C50644808 @default.
- W4386847536 hasConceptScore W4386847536C58973888 @default.
- W4386847536 hasConceptScore W4386847536C64543145 @default.
- W4386847536 hasFunder F4320310339 @default.
- W4386847536 hasLocation W43868475361 @default.
- W4386847536 hasOpenAccess W4386847536 @default.
- W4386847536 hasPrimaryLocation W43868475361 @default.
- W4386847536 hasRelatedWork W122912556 @default.
- W4386847536 hasRelatedWork W1756896031 @default.
- W4386847536 hasRelatedWork W2031481712 @default.
- W4386847536 hasRelatedWork W2531570999 @default.
- W4386847536 hasRelatedWork W3162567751 @default.
- W4386847536 hasRelatedWork W3178565231 @default.
- W4386847536 hasRelatedWork W4285260836 @default.
- W4386847536 hasRelatedWork W4287100511 @default.
- W4386847536 hasRelatedWork W4312414840 @default.
- W4386847536 hasRelatedWork W4319309271 @default.
- W4386847536 isParatext "false" @default.