Remote　sensing　image　retrieval　is　an　effective　means　to　manage　and　share　massive　remote　sensing　image　data.　In　this　paper,　a　remote　sensing　image　retrieval　method　has　been　proposed,　which　adopts　Inception　V4　as　the　backbone　network　to　extract　the　deep　features.　To　represent　the　low-level　visual　information　of　the　remote　sensing　image,　the　feature　maps　generated　from　the　first　Reduction　Block　of　Inception　V4　through　using　5　×　5　convolutional　kernels　are　extracted　and　reorganized.　Next,　VLAD　(Vector　Locally　Aggregated　Descriptors)　is　exploited　to　encode　the　reorganized　features　to　obtain　a　compact　feature　representation　vector.　The　vector　is　cascaded　with　the　features　extracted　from　the　fully　connected　layers　to　form　the　overall　feature　vector　of　the　image.　In　order　to　avoid　the　problem　of　＇Curse　of　Dimensionality＇,　Largevis　dimensionality　reduction　method　is　utilized　to　reduce　the　dimensionality　of　the　image　feature　vector,　while　improving　its　discriminative　capability.　The　dimensionality　reduced　feature　vector　is　utilized　for　image　retrieval　with　L2　distance　measurement　metric.　Experimental　results　on　the　datasets　of　RS19,　UCM　and　RSSCN7　have　demonstrated　that,　compared　with　the　existing　methods,　the　proposed　method　can　obtain　state-of-the-art　retrieval　performance.　©　2021,　The　Author(s),　under　exclusive　licence　to　Springer　Science+Business　Media,　LLC,　part　of　Springer　Nature.