44 citations · 97 across the 9 of their papers we have counts for
9 papers
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Bo Jiang, Shaoyu Chen, Qing Xu +7
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representat…
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…
MixSKD: Self-Knowledge Distillation from Mixup for Image Recognition
Chuanguang Yang, Zhulin An, Helong Zhou +5
Unlike the conventional Knowledge Distillation (KD), Self-KD allows a network to learn knowledge from itself without any guidance from extra networks. This paper proposes to perfor…
Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition
Chuanguang Yang, Zhulin An, Helong Zhou +3
The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing on…
HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction
Yihan Hu, Wenxin Shao, Bo Jiang +6
In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard. We h…
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…