Few-shot　object　detection　aims　to　rapidly　detect　novel　classes　of　objects　using　a　minimal　number　of　annotated　instances.　Compared　to　methods　such　as　meta-learning,　few-shot　object　detection　based　on　transfer　learning　can　achieve　better　performance.　However,　when　training　on　base-class　datasets,　the　model　gradually　improves　its　detection　performance　on　base　classes　but　does　not　enhance　its　generalization.　A　base-class　model　lacking　generalization　tends　to　result　in　lower　detection　performance　for　novel　classes　during　fine-tuning.　To　address　the　aforementioned　issues,　this　paper　tackles　the　problem　from　two　aspects:　firstly,　we　introduce　the　Confusion-Dropblock　Module　(CDM)　to　perturb　the　model＇s　features,　thus　enhancing　feature　generalization.　Secondly,　we　incorporate　Deformable　Convolution　Modules　to　mitigate　the　impact　of　object　shapes　and　sizes　on　detection　performance,　thereby　improving　overall　detection　performance.　Experimental　results　on　the　COCO　dataset　demonstrate　the　effectiveness　of　the　proposed　algorithm,　outperforming　the　compared　methods.　©　2023　IEEE.