Abstract: The defect detection for photovoltaic module electroluminescence images is a challenging task,due to two difficulties,tiny and weak. To address this problem,the Multi-Scale Encoding Complementary Attention Network（MCECAN） is designed. The backbone and prediction head of MCECAN follow the YOLO series design,but the network neck applies the Multi-Scale Coding Complementary Attention Module（MCECAM）. The front-end of the module uses a multi-scale encoder to aggregate multi-scale information and enhance global information. The back-end complementary coordinate attention establishes the dependency between feature map channels,highlights defect features,suppresses background interference,and improves the ability of network to detect tiny and weak targets. On a dataset containing 5537 EL defect images,the MCECAN shows the best detection performance.