<p>Knowledge distillation has proven to be an effective technique for enhancing object detection performance. However, the presence of different detector types often results in a significant performance gap between teacher and student models. In this paper, we propose an Instance Mask Alignment (IMA) knowledge distillation framework for object detection. Our framework leverages knowledge transformation operations to reduce the teacher-student gap, leading to notable performance improvements. We introduce instance mask distillation, which incorporates mask information to enhance the student model’s ability to identify and focus on relevant regions or objects. Additionally, we introduce a cascade alignment module with instance standardization, utilizing an adaptive scale deflation module along the instance dimension. Through the integration of these cascade knowledge alignment modules, our proposed framework achieves substantial performance gains across various detector types. Extensive experiments conducted on the MS-COCO, PASCAL VOC and Cityscapes benchmarks demonstrate the effectiveness of our novel method, particularly its adaptability to heterogeneous detectors.</p>