Jiaxin Liu

Jiaxin Liu

Auto-generated profile, based on publicly available information

Jiaxin Liu

School of Computer Science and Engineering, Northeastern University, Shenyang, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2024 in IEEE Access
Verified
Journal Article
Open access
SCShuai Cheng
Shuai Cheng
ZNZuotao Ning
Zuotao Ning
JHJun Hu
Jun Hu
JLJiaxin Liu
Jiaxin Liu
WYWenxing Yang
Wenxing Yang
WLWei Liu
Wei Liu
Detection based on LiDAR and camera fusion is increasingly popular for researchers in the autonomous driving domain. Compared to the camera-only and LiDAR-only methods, the fusion-based methods indeed improve the detection accuracy on public-available datasets. However, due to the complexity of the projection or fusion mechanism, few of these methods can run in real time even on an advanced desktop GPU. Thus, in this paper, we propose a new fusion detection model G-Fusion with a light and fast image view-transform module. According to our receptive field analysis of image feature maps, we directly project image features to only one voxel layer located on the ground, then fuse the LiDAR and image features by concatenation and convolution. With this delicately designed module, G-Fusion greatly boosts the state-of-the-art speed performance on the nuScenes dataset, achieving a good balance with the competitive detection scores. Meanwhile, since the precision of sensor extrinsic parameters is important for most fusion-based methods, we also deeply dig into our model’s calibration error tolerance ability and discover the failure noise condition.

18 June 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJiaxin Liu
Jiaxin Liu
PWPengyu Wang
Pengyu Wang
ALAnd Wei Liu
And Wei Liu
SDShangwei Du
Shangwei Du
Yongming LiYongming Li
Yongming Li
SCShuai Cheng
Shuai Cheng
Bird’s Eye View (BEV) perception requires swift and accurate representation of real-world 3D information, and BEV-based 3D object detection and semantic segmentation are foundational for downstream autonomous tasks such as prediction and planning. Current BEV perception methods are divided into Light Detection and Ranging(LiDAR)-based and camera-based methods depending on the input data modalities. LiDAR-based methods offer precise 3D information, but are limited by high sensor costs. Conversely, camera-based methods are economical and widely researched. However, 2D image features transform into BEV space introducing feature distortion due to inaccurate 3D information, particularly in depth estimation which results in noisy projections. Denoising Diffusion Probabilistic Models (DDPM) are used to mitigate noise in BEV features. However, DDPM increases computational costs, relies on noisy images BEV features, and limits effectiveness. To address these issues, we propose a lightweight BEV perception framework (DMPG-BEV) to enhance the performance of camera-based methods. This framework employs Denoising Diffusion Implicit Models (DDIM) to generate point cloud features with 3D information, while reducing computational demands by fewer denoising steps. We also introduce a lightweight feature fusion module which integrates point cloud BEV features with image BEV features to incorporate 3D information and reduce noise. The refined BEV features are also well-suited for multi-task networks involving detection and segmentation tasks. Additionally, a lightweight view transformation module is included to further reduce computational costs. Extensive experiments on the nuScenes benchmark demonstrate better performance of our proposed model with reduced computation, highlighting its value in BEV perception.

17 August 2023 in IEEE Access
Verified
Journal Article
Open access
PWPengyu Wang
Pengyu Wang
TRTao Ren
Tao Ren
JLJiaxin Liu
Jiaxin Liu
FMFanchun Meng
Fanchun Meng
XLXinliang Liu
Xinliang Liu
WLWei Liu
Wei Liu
The prevalence of convolutional neural networks is hindered by their intricate structure and voluminous parameters, which consume significant processing resources during both training and inference. This study proposes a novel approach that involves treating convolutional kernels as tensors, utilizing suitable priori metrics to gauge their effectiveness, and employing a clustering algorithm to eliminate redundant convolutional kernels for network pruning. To measure the convolutional kernels, we use appropriate priori metrics and density-Based spatial clustering of applications with noise (DBSCAN) to cluster the convolutional kernels so that the cluster centroids are the reserved convolution kernels. The experimental results show that the method can effectively perform network lightweight while maintaining high accuracy. At the same time, the method can improve the efficiency of convolutional kernel utilization, thus reducing the computational resource consumption of the model. Empirical analyses conducted on datasets indicate that, in certain instances, the proposed pruning method outperforms established state-of-the-art methods.

25 December 2023
Verified
Book Chapter
Closed access
PDF file
JLJiaxin Liu
Jiaxin Liu
DZDazong Zhang
Dazong Zhang
WLWei Liu
Wei Liu
YLYongming Li
Yongming Li
JHJun Hu
Jun Hu
WYWenxing Yang
Wenxing Yang

23 February 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJiaxin Liu
Jiaxin Liu
ALAnd Wei Liu
And Wei Liu
PWPengyu Wang
Pengyu Wang
Yongming LiYongming Li
Yongming Li
JHJun Hu
Jun Hu
WYWenxing Yang
Wenxing Yang
Multi-camera 3D object detection receives extensive attention in autonomous driving because of its advantage in efficiency and cost-effectiveness. However, a performance gap still exists between camera-based detector and LiDAR-based detector. Because camera-based detector cannot extract precise depth and geometric information from the input image data, resulting in obvious projection deviation when transforming features from the perspective view to the bird’s eye view (BEV). We propose a cross-modal knowledge distillation framework (DFPR-BEV) to address this problem, making the camera-based student detector to improve its feature representation by imitating the trained LiDAR-based teacher detector during training. To prevent semantic information from being harmed by directly aligning features during distillation by modal variation, we improve the student model to decouple point clouds feature distillation and image projection position correction. A heatmap-based projection correction method is proposed to correct image feature projection deviation and eliminate conflicting features. A Gaussian mixture region-based method is introduced for comprehensive geometry and depth transmission of point clouds features. Finally, the detection performance is improved by effectively fusing the two distilled features. Extensive experiments on nuScenes benchmark illustrate that DFPR-BEV can significantly improve the performance of the student model, outperforming current distillation methods and other camera-based detectors with equal or lower computational budget. Notably, on the nuScenes val set after distillation, BEVDet’s NDS and mAP are improved by 4.9% and 4.2%, respectively, BEVDet4D’s inference speed is 5× faster than BEVFormer-S with the same mAP and higher NDS.