1 citations · 1 across the 6 of their papers we have counts for
6 papers
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Jun Li, Yingying Shi, Zhixuan Ruan +2
In a real-world traffic scenario, varying-scale objects are usually distributed in a cluttered background, which poses great challenges to accurate detection. Although current Mamb…
InceptionMamba: An Efficient Hybrid Network with Large Band Convolution and Bottleneck Mamba
Yuhang Wang, Jun Li, Zhijian Wu +3
Within the family of convolutional neural networks, InceptionNeXt has shown excellent competitiveness in image classification and a number of downstream tasks. Built on parallel on…
Progressive Class-level Distillation
Jiayan Li, Jun Li, Zhourui Zhang +1
In knowledge distillation (KD), logit distillation (LD) aims to transfer class-level knowledge from a more powerful teacher network to a small student model via accurate teacher-st…
SAMKD: Spatial-aware Adaptive Masking Knowledge Distillation for Object Detection
Zhourui Zhang, Jun Li, Jiayan Li +1
Most of recent attention-guided feature masking distillation methods perform knowledge transfer via global teacher attention maps without delving into fine-grained clues. Instead,…
DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection
Zhourui Zhang, Jun Li, Zhijian Wu +2
In recent years, current mainstream feature masking distillation methods mainly function by reconstructing selectively masked regions of a student network from the feature maps of…
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…