most citedDMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cond-mat.mtrl-sci2023

Janus-graphene: a two-dimensional half-auxetic carbon allotropes with non-chemical Janus configuration

Linfeng Yu, Jianhua Xu, Chen Shen +5

The asymmetric properties of Janus two-dimensional materials commonly depend on chemical effects, such as different atoms, elements, material types, etc. Herein, based on carbon ge…

cs.CV20231 cited

DMKD: Improving Feature-based Knowledge Distillation for Object Detection Via Dual Masking Augmentation

Guang Yang, Yin Tang, Zhijian Wu +3

Recent mainstream masked distillation methods function by reconstructing selectively masked areas of a student network from the feature map of its teacher counterpart. In these met…

cs.CV2023

EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection

Guangtao Wang, Jun Li, Jie Xie +2

In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks. They usually contain limited v…

cs.CV2023

LogoNet: a fine-grained network for instance-level logo sketch retrieval

Binbin Feng, Jun Li, Jianhua Xu

Sketch-based image retrieval, which aims to use sketches as queries to retrieve images containing the same query instance, receives increasing attention in recent years. Although d…

cs.CV2023

EfficientFace: An Efficient Deep Network with Feature Enhancement for Accurate Face Detection

Guangtao Wang, Jun Li, Zhijian Wu +3

In recent years, deep convolutional neural networks (CNN) have significantly advanced face detection. In particular, lightweight CNNbased architectures have achieved great success…

cs.CV2023

AMD: Adaptive Masked Distillation for Object Detection

Guang Yang, Yin Tang, Jun Li +2

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…