QingHao Meng

Qinghao Meng, Chenming Wu, Liangjun Zhang et al.

3D object detection is essential in autonomous driving, providing vital information about moving objects and obstacles. Detecting objects in distant regions with only a few LiDAR points is still a challenge, and numerous strategies have been developed to address point cloud sparsity through densification.This paper presents a joint completion and detection framework that improves the detection feature in sparse areas while maintaining costs unchanged. Specifically, we propose TransBridge, a novel transformer-based up-sampling block that fuses the features from the detection and completion networks.The detection network can benefit from acquiring implicit completion features derived from the completion network. Additionally, we design the Dynamic-Static Reconstruction (DSRecon) module to produce dense LiDAR data for the completion network, meeting the requirement for dense point cloud ground truth.Furthermore, we employ the transformer mechanism to establish connections between channels and spatial relations, resulting in a high-resolution feature map used for completion purposes.Extensive experiments on the nuScenes and Waymo datasets demonstrate the effectiveness of the proposed framework.The results show that our framework consistently improves end-to-end 3D object detection, with the mean average precision (mAP) ranging from 0.7 to 1.5 across multiple methods, indicating its generalization ability. For the two-stage detection framework, it also boosts the mAP up to 5.78 points.

ZhongYi Zhang, ChenYang Xu, LiXuan Zhao et al.

Electroencephalogram (EEG) is a non-invasive tool for real-time neural monitoring,widely used in depression detection via deep learning. However, existing models primarily focus on binary classification (depression/normal), lacking granularity for severity assessment. To address this, we proposed the DepL-GCN, i.e., Depression Level classification based on GCN model. This model tackles two key challenges: (1) subjectivity in depres-sion-level labeling due to patient self-report biases, and (2) class imbalance across severity categories. Inspired by the model learning patterns, we introduced two novel modules: the sample confidence module and the minority sample penalty module. The former leverages the L2-norm of prediction errors to progressively filter EEG samples with weak label alignment during training, thereby reducing the impact of subjectivity; the latter automatically upweights misclassified minority-class samples to address imbalance issues. After testing on two public EEG datasets, DepL-GCN achieved accuracies of 81.13% and 81.36% for multi-class severity recognition, outperforming baseline models.Ablation studies confirmed both modules' contributions. We further discussed the strengths and limitations of regression-based models for depression-level recognition.

Qinghao Meng, Wenguan Wang, Tianfei Zhou et al.

It is laborious to manually label point cloud data for training high-quality 3D object detectors. This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances. This is achieved by a two-stage architecture design. Stage-1 learns to generate cylindrical object proposals under weak supervision, i.e., only the horizontal centers of objects are click-annotated on bird's view scenes. Stage-2 learns to refine the cylindrical proposals to get cuboids and confidence scores, using a few well-labeled object instances. Using only 500 weakly annotated scenes and 534 precisely labeled vehicle instances, our method achieves 85-95% the performance of current top-leading, fully supervised detectors (which require 3, 712 exhaustively and precisely annotated scenes with 15, 654 instances). More importantly, with our elaborately designed network architecture, our trained model can be applied as a 3D object annotator, allowing both automatic and active working modes. The annotations generated by our model can be used to train 3D object detectors with over 94% of their original performance (under manually labeled data). Our experiments also show our model's potential in boosting performance given more training data. Above designs make our approach highly practical and introduce new opportunities for learning 3D object detection with reduced annotation burden.

Junbo Yin, Wenguan Wang, Qinghao Meng et al.

Current popular online multi-object tracking (MOT) solutions apply single object trackers (SOTs) to capture object motions, while often requiring an extra affinity network to associate objects, especially for the occluded ones. This brings extra computational overhead due to repetitive feature extraction for SOT and affinity computation. Meanwhile, the model size of the sophisticated affinity network is usually non-trivial. In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure. In particular, UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. Such design brings advantages of improved computation efficiency, low memory requirement and simplified training procedure. In addition, we equip our model with a task-specific attention module, which is used to boost task-aware feature learning. The proposed UMA can be easily trained end-to-end, and is elegant - requiring only one training stage. Experimental results show that it achieves promising performance on several MOT Challenge benchmarks.