262 citations · 1.1k across the 24 of their papers we have counts for
24 papers
ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transformers
Changjun Li, Runqing Jiang, Lian Xu +3
Vision Transformers have achieved remarkable success in many fields, yet their deployment on edge devices remains challenging due to their substantial computational demands. Post-T…
MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias
Xingming Li, Ao Cheng, Qiyao Sun +4
When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applica…
PVP: Pre-trained Visual Parameter-Efficient Tuning
Zhao Song, Ke Yang, Naiyang Guan +3
Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models…
Small but Mighty: Enhancing 3D Point Clouds Semantic Segmentation with U-Next Framework
Ziyin Zeng, Qingyong Hu, Zhong Xie +2
We study the problem of semantic segmentation of large-scale 3D point clouds. In recent years, significant research efforts have been directed toward local feature aggregation, imp…
Backdoor Defense via Deconfounded Representation Learning
Zaixi Zhang, Qi Liu, Zhicai Wang +2
Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples in…
Hierarchical Graph Transformer with Adaptive Node Sampling
Zaixi Zhang, Qi Liu, Qingyong Hu +1
The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-struc…
DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction
Kaichen Zhou, Lanqing Hong, Changhao Chen +4
Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully…
4DAC: Learning Attribute Compression for Dynamic Point Clouds
Guangchi Fang, Qingyong Hu, Yiling Xu +1
With the development of the 3D data acquisition facilities, the increasing scale of acquired 3D point clouds poses a challenge to the existing data compression techniques. Although…
Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds
Ta-Ying Cheng, Qingyong Hu, Qian Xie +2
Sampling is a key operation in point-cloud task and acts to increase computational efficiency and tractability by discarding redundant points. Universal sampling algorithms (e.g.,…
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
Jia-Xing Zhong, Kaichen Zhou, Qingyong Hu +3
Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification…
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
Yifan Zhang, Qingyong Hu, Guoquan Xu +3
We study the problem of efficient object detection of 3D LiDAR point clouds. To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic…
3DAC: Learning Attribute Compression for Point Clouds
Guangchi Fang, Qingyong Hu, Hanyun Wang +2
We study the problem of attribute compression for large-scale unstructured 3D point clouds. Through an in-depth exploration of the relationships between different encoding steps an…
STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
Meida Chen, Qingyong Hu, Zifan Yu +6
Although various 3D datasets with different functions and scales have been proposed recently, it remains challenging for individuals to complete the whole pipeline of large-scale d…
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds
Qingyong Hu, Bo Yang, Sheikh Khalid +3
With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to fa…
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Yan Liu, Qingyong Hu, Yinjie Lei +3
Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly…
Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
Qian Yin, Qingyong Hu, Hao Liu +5
Satellite video cameras can provide continuous observation for a large-scale area, which is important for many remote sensing applications. However, achieving moving object detecti…
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
Qingyong Hu, Bo Yang, Linhai Xie +5
We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing ste…
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Qingyong Hu, Bo Yang, Guangchi Fang +4
Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is e…
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Sheng Ao, Qingyong Hu, Bo Yang +2
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either…
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
Qingyong Hu, Bo Yang, Sheikh Khalid +3
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly an…
Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
Ruigang Fu, Qingyong Hu, Xiaohu Dong +3
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years. In…
Deep Learning for 3D Point Clouds: A Survey
Yulan Guo, Hanyun Wang, Qingyong Hu +3
Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominatin…
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
Qingyong Hu, Bo Yang, Linhai Xie +5
We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing st…
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
Bo Yang, Jianan Wang, Ronald Clark +4
We propose a novel, conceptually simple and general framework for instance segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the simple design philosophy of per…