output
20162023
most citedRethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective

44 citations

Showing cs.CVShow all

11 papers · 1 filter

cs.CV20228 cited

Towards Accurate Ground Plane Normal Estimation from Ego-Motion

Jiaxin Zhang, Wei Sui, Qian Zhang +2

In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles. In practice, the ground plane is dynamically changed due to braking and unstabl…

cs.CV202210 cited

ELMformer: Efficient Raw Image Restoration with a Locally Multiplicative Transformer

Jiaqi Ma, Shengyuan Yan, Lefei Zhang +2

In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for…

cs.CV202126 cited

Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation

Xinggang Wang, Zhaojin Huang, Bencheng Liao +3

Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for p…

cs.CV202117 cited

Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition

Mengting Chen, Xinggang Wang, Heng Luo +2

Deep networks can learn to accurately recognize objects of a category by training on a large number of annotated images. However, a meta-learning challenge known as a low-shot imag…

cs.CV20202 cited

Gaussian Vector: An Efficient Solution for Facial Landmark Detection

Yilin Xiong, Zijian Zhou, Yuhao Dou +1

Significant progress has been made in facial landmark detection with the development of Convolutional Neural Networks. The widely-used algorithms can be classified into coordinate…

cs.CV202042 cited

Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining

Yiqun Mei, Yuchen Fan, Yuqian Zhou +3

Deep convolution-based single image super-resolution (SISR) networks embrace the benefits of learning from large-scale external image resources for local recovery, yet most existin…