AMD: Adaptive Masked Distillation for Object Detection

TL;DR

This paper introduces AMD, a novel feature distillation framework for object detection that uses spatial-channel adaptive masking to improve student model performance, outperforming previous methods.

Contribution

The paper proposes a spatial-channel adaptive masked distillation network that enhances feature reconstruction for object detection, surpassing prior distillation techniques.

Findings

Student models achieve higher mAP scores with AMD.

AMD outperforms previous distillation methods like FGD and MGD.

The method improves object perception and detection capabilities.

Abstract

As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we mainly focus on designing an effective feature-distillation framework and propose a spatial-channel adaptive masked distillation (AMD) network for object detection. More specifically, in order to accurately reconstruct important feature regions, we first perform attention-guided feature masking on the feature map of the student network, such that we can identify the important features via spatially adaptive feature masking instead of random masking in the previous methods. In addition, we employ a simple and efficient module to allow the student network channel to be adaptive, improving its model capability in object perception and detection. In contrast to the previous methods, more crucial object-aware features can be reconstructed and learned from the proposed network, which is conducive to accurate object detection. The empirical experiments demonstrate the superiority of our method: with the help of our proposed distillation method, the student networks report 41.3%, 42.4%, and 42.7% mAP scores when RetinaNet, Cascade Mask-RCNN and RepPoints are respectively used as the teacher framework for object detection, which outperforms the previous state-of-the-art distillation methods including FGD and MGD.