44 citations · 57 across the 4 of their papers we have counts for
5 papers
Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction
Bo Jiang, Shaoyu Chen, Xinggang Wang +7
Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first en…
Cross-Image Relational Knowledge Distillation for Semantic Segmentation
Chuanguang Yang, Helong Zhou, Zhulin An +3
Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples.…
Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition
Xichen Pan, Peiyu Chen, Yichen Gong +3
Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual s…
Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective
Helong Zhou, Liangchen Song, Jiajie Chen +4
Knowledge distillation is an effective approach to leverage a well-trained network or an ensemble of them, named as the teacher, to guide the training of a student network. The out…
VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing
Qian Zhang, Jianjun Li, Meng Yao +6
In this paper, we propose a novel network design mechanism for efficient embedded computing. Inspired by the limited computing patterns, we propose to fix the number of channels in…