507 citations · 2.3k across the 101 of their papers we have counts for
13 papers · 1 filter
Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection
Tianchen Zhao, Xuefei Ning, Ke Hong +8
Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. However, their significant computational and memory costs pose a chall…
Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
Tianli Zhang, Mengqi Xue, Jiangtao Zhang +5
Most existing online knowledge distillation(OKD) techniques typically require sophisticated modules to produce diverse knowledge for improving students' generalization ability. In…
LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception
Zixiang Zhou, Dongqiangzi Ye, Weijia Chen +4
There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks fo…
Detecting Objects with Context-Likelihood Graphs and Graph Refinement
Aritra Bhowmik, Yu Wang, Nora Baka +2
The goal of this paper is to detect objects by exploiting their interrelationships. Contrary to existing methods, which learn objects and relations separately, our key idea is to l…
SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
Zhaofan Qiu, Yehao Li, Yu Wang +3
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies…
Cross-layer Attention Network for Fine-grained Visual Categorization
Ranran Huang, Yu Wang, Huazhong Yang
Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC). Compared to previous attention-based wor…
CenterFormer: Center-based Transformer for 3D Object Detection
Zixiang Zhou, Xiangchen Zhao, Yu Wang +2
Query-based transformer has shown great potential in constructing long-range attention in many image-domain tasks, but has rarely been considered in LiDAR-based 3D object detection…
LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception
Dongqiangzi Ye, Zixiang Zhou, Weijia Chen +4
LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are usually implemented in specialized networks with distinctive architectures that are difficult…
CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS
Zixuan Zhou, Xuefei Ning, Yi Cai +5
One-shot Neural Architecture Search (NAS) has been widely used to discover architectures due to its efficiency. However, previous studies reveal that one-shot performance estimatio…
Dual Vision Transformer
Ting Yao, Yehao Li, Yingwei Pan +3
Prior works have proposed several strategies to reduce the computational cost of self-attention mechanism. Many of these works consider decomposing the self-attention procedure int…
LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network
Dongqiangzi Ye, Weijia Chen, Zixiang Zhou +4
This technical report presents the 1st place winning solution for the Waymo Open Dataset 3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the maj…
LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
Yu Wang, Quan Zhou, Jia Liu +4
The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,na…
Transferrable Prototypical Networks for Unsupervised Domain Adaptation
Yingwei Pan, Ting Yao, Yehao Li +3
In this paper, we introduce a new idea for unsupervised domain adaptation via a remold of Prototypical Networks, which learn an embedding space and perform classification via a rem…