AMD: Adaptive Masked Distillation for Object

Abstract

As a general model compression paradigm, featurebased 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.

SFDet: spatial to frequency attention for small-object detection in underwater images

“…As a feature-based knowledge distillation paradigm, the adaptive mask extraction network proposed in Ref. 13 can reconstruct and learn more critical object-aware features, which is helpful for the accuracy of small-object detection. By contrast, our approach seeks to enhance the performance of small-object detection by including frequency domain branches to compensate for the lack of information in the spatial domain.…”