多彩娱乐城-威尼斯人娱乐骰宝-足球现金网平台出租

Deep unfolding methods in image inverse problems: some algorithm and theoretical advances

發(fā)布時(shí)間:2025-12-10 供稿單位:數(shù)學(xué)與統(tǒng)計(jì)學(xué)院 點(diǎn)擊次數(shù):

標(biāo)題:Deep unfolding methods in image inverse problems: some algorithm and theoretical advances

報(bào)告時(shí)間:2025年12月12星期9:00-10:00

報(bào)告地點(diǎn):線(xiàn)上騰訊會(huì)議會(huì)議ID:933-995-317

主講人:  吳春林

主辦單位:數(shù)學(xué)與統(tǒng)計(jì)學(xué)院

報(bào)告內(nèi)容簡(jiǎn)介:

Deep unfolding methods are an important kind of methods in image inverse problems. They combine well mathematical modeling and data-driven spirits, and provide a good strategy to construct interpretable learning-based methods.In this talk, we will discuss some recent advances in such methods. We will in particular present our recent L1DecNet+ architecture for object segmentation based on sparse regularization, as well as dynamical system analysis (stability and deep layer limit) of learned primal-dual.

主講人簡(jiǎn)介:

吳春林,南開(kāi)大學(xué)數(shù)學(xué)科學(xué)學(xué)院教授、博導(dǎo)。研究興趣為圖像反問(wèn)題、稀疏優(yōu)化、深度學(xué)習(xí)中的基礎(chǔ)理論與算法。于2001年和2006年在中國(guó)科學(xué)技術(shù)大學(xué)獲得學(xué)士和博士學(xué)位。曾在中國(guó)科學(xué)技術(shù)大學(xué),新加坡南洋理工大學(xué),新加坡國(guó)立大學(xué)從事博士后研究工作。2012年加入南開(kāi)大學(xué)。入選國(guó)家高層次人才青年項(xiàng)目,主持多項(xiàng)國(guó)家級(jí)與省部級(jí)基金項(xiàng)目。(曾)任中國(guó)數(shù)學(xué)會(huì)計(jì)算數(shù)學(xué)分會(huì)常務(wù)理事、天津市數(shù)學(xué)會(huì)計(jì)算數(shù)學(xué)分會(huì)理事長(zhǎng)、中國(guó)運(yùn)籌學(xué)會(huì)數(shù)學(xué)規(guī)劃分會(huì)理事、中國(guó)運(yùn)籌學(xué)會(huì)算法軟件與應(yīng)用分會(huì)理事、天津市數(shù)學(xué)會(huì)理事、天津市工業(yè)與應(yīng)用數(shù)學(xué)會(huì)理事、南開(kāi)大學(xué)數(shù)學(xué)科學(xué)學(xué)院副院長(zhǎng),國(guó)際期刊Advances in Continuous and Discrete Models編委。