110 citations · 584 across the 45 of their papers we have counts for
5 papers · 1 filter
Channel-wise Knowledge Distillation for Dense Prediction
Changyong Shu, Yifan Liu, Jianfei Gao +2
Knowledge distillation (KD) has been proven to be a simple and effective tool for training compact models. Almost all KD variants for dense prediction tasks align the student and t…
Representative Graph Neural Network
Changqian Yu, Yifan Liu, Changxin Gao +2
Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper,…
DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
Wei Yin, Xinlong Wang, Chunhua Shen +5
We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shap…
Crowd Counting via Hierarchical Scale Recalibration Network
Zhikang Zou, Yifan Liu, Shuangjie Xu +3
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenati…
Efficient Semantic Video Segmentation with Per-frame Inference
Yifan Liu, Chunhua Shen, Changqian Yu +1
For semantic segmentation, most existing real-time deep models trained with each frame independently may produce inconsistent results for a video sequence. Advanced methods take in…