270 citations · 591 across the 48 of their papers we have counts for
12 papers · 1 filter
MINIMA: Modality Invariant Image Matching
Jiangwei Ren, Xingyu Jiang, Zizhuo Li +3
Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses…
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Dingkang Liang, Tianrui Feng, Xin Zhou +3
Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of…
Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression
Dingyuan Zhang, Dingkang Liang, Zichang Tan +4
Slow inference speed is one of the most crucial concerns for deploying multi-view 3D detectors to tasks with high real-time requirements like autonomous driving. Although many spar…
Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid
Mingxin Huang, Yuliang Liu, Dingkang Liang +2
Recently, scaling images to high resolution has received much attention in multimodal large language models (MLLMs). Most existing practices adopt a sliding-window-style cropping s…
A Unified Framework for 3D Scene Understanding
Wei Xu, Chunsheng Shi, Sifan Tu +3
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a…
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Dingkang Liang, Wei Hua, Chunsheng Shi +3
Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on hor…
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Xingkui Zhu, Yiran Guan, Dingkang Liang +3
The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational eff…
Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis
Xin Zhou, Dingkang Liang, Wei Xu +4
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model pa…
Anomaly Detection by Adapting a pre-trained Vision Language Model
Yuxuan Cai, Xinwei He, Dingkang Liang +2
Recently, large vision and language models have shown their success when adapting them to many downstream tasks. In this paper, we present a unified framework named CLIP-ADA for An…
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding
Hongcheng Yang, Dingkang Liang, Dingyuan Zhang +4
The recent advancements in point cloud learning have enabled intelligent vehicles and robots to comprehend 3D environments better. However, processing large-scale 3D scenes remains…
PointMamba: A Simple State Space Model for Point Cloud Analysis
Dingkang Liang, Xin Zhou, Wei Xu +5
Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has qu…
You Only Look Bottom-Up for Monocular 3D Object Detection
Kaixin Xiong, Dingyuan Zhang, Dingkang Liang +5
Monocular 3D Object Detection is an essential task for autonomous driving. Meanwhile, accurate 3D object detection from pure images is very challenging due to the loss of depth inf…