The invention discloses an improved Mask R-CNN image instance segmentation method for identifying defects of power equipment. The method comprises the steps of constructing a convolutional neural network; reading the power equipment defect pre-processed picture, inputting the power equipment defect pre-processed picture into a convolutional neural network, and performing feature extraction on thepower equipment defect pre-processed picture by the convolutional neural network to obtain a feature-containing region; refining the region containing the characteristics through an RPN network; and in the refined region, carrying out RoIAgign operation through a bilinear difference method to process the refined region, generating a feature map of a fixed size for each region of interest, and obtaining power equipment defect instance segmentation through the category, the coordinate information and the mask information. By improving the Mask R-CNN image instance segmentation method, the basiceffect of Mask R-CNN segmentation is reserved, the bilinear interpolation speed in the RoIAgign process is increased, meanwhile, the mapping process fully and uniformly utilizes power equipment defects to preprocess all pixels of an image, and the segmentation effect is more obvious.