原创力文档- 1、本文档被系统程序自动判定探测到侵权嫌疑，本站暂时做下架处理。
- 2、如果您确认为侵权，可联系本站左侧在线QQ客服请求删除。我们会保证在24小时内做出处理，应急电话：400-050-0827。
- 3、此文档由网友上传，因疑似侵权的原因，本站不提供该文档下载，只提供部分内容试读。如果您是出版社/作者，看到后可认领文档，您也可以联系本站进行批量认领。
InferentialMachineLearning:TowardsHuman-
collaborativeVisionandLanguageModels
GhassanAlRegib,PhDMohitPrabhushankar,PhDXiaoqianWang,PhD
ProfessorPostdoctoralFellowAssistantProfessor
OmniLabforIntelligentVisualEngineeringandScience(OLIVES)ElectricalandComputerEngineering
SchoolofElectricalandComputerEngineeringPurdueUniversity
GeorgiaInstituteofTechnologyjoywang@
{alregib,mohit.p}@
Feb.26,2025–Philadelphia,USA
TutorialMaterials
AccessibleOnline
/courses-
and-tutorials/aaai-2025-tutorial/
{alregib,mohit.p}@,
joywang@
2of195[Tutorial@AAAI25]|[GhassanAlRegib,MohitPrabhushankar,andJoyWang]|[Feb26,2025]
FoundationModels
ExpectationvsReality
ExpectationvsRealityofFoundationModels
3of195[Tutorial@AAAI25]|[GhassanAlRegib,MohitPrabhushankar,andJoyWang]|[Feb26,2025]
FoundationModels
SegmentAnythingModel
SegmentAnythingModel(SAM)releasedbyMetaonApril5,2023wastrainedonSegmentAnything1Billion
datasetwith1.1billionhigh-qualitysegmentationmasksfrom11millionimages
4of195[Tutorial@AAAI25]|[GhassanAlRegib,MohitPrabhushankar,andJoyWang]|[Feb26,2025]
Kirillov,Alexander,EricMintun,NikhilaRavi,HanziMao,ChloeRolland,LauraGustafson,TeteXiaoetal.
Segmentanything.arXivpreprintarXiv:2304.02643(2023).
FoundationModels
SegmentAnythingModel
Cityscapesdataset
文档评论（0）