1. [Publications](/publications)
2. Data-Free Knowledge Distillation for Object Detection
 
 # Data-Free Knowledge Distillation for Object Detection

  ![](/sites/default/files/styles/wide/public/publications/Screen%20Shot%202021-10-13%20at%204.24.01%20PM.png?itok=fSOwJuwf)

 We present DeepInversion for Object Detection (DIODE) to enable data-free knowledge distillation for neural networks trained on the object detection task. From a data-free perspective, DIODE synthesizes images given only an off-the-shelf pre-trained detection network and without any prior domain knowledge, generator network, or pre-computed activations. DIODE relies on two key components--first, an extensive set of differentiable augmentations to improve image fidelity and distillation effectiveness. Second, a novel automated bounding box and category sampling scheme for image synthesis enabling generating a large number of images with a diverse set of spatial and category objects. The resulting images enable data-free knowledge distillation from a teacher to a student detector, initialized from scratch. In an extensive set of experiments, we demonstrate that DIODE's ability to match the original training distribution consistently enables more effective knowledge distillation than out-of-distribution proxy datasets, which unavoidably occur in a data-free setup given the absence of the original domain knowledge.



 ## Authors



Akshay Chawla (CMU)

[Hongxu Danny Yin](/person/danny-yin)

[Pavlo Molchanov](/person/pavlo-molchanov)

Jose M. Alvarez (NVIDIA)

 

 

 ## Publication Date



Tuesday, January 5, 2021

 

 ## Published in



[WACV 2021](https://openaccess.thecvf.com/content/WACV2021/html/Chawla_Data-Free_Knowledge_Distillation_for_Object_Detection_WACV_2021_paper.html)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)