Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Liang, Dingkang"'
Recently, there has been significant interest in enhancing the capability of multimodal large language models (MLLMs) to process high-resolution images. Most existing methods focus on adopting a cropping strategy to improve the ability of multimodal
Externí odkaz:
http://arxiv.org/abs/2408.02034
We propose UniSeg3D, a unified 3D segmentation framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary semantic segmentation tasks within a single model. Most previous 3D segmentation approaches are specializ
Externí odkaz:
http://arxiv.org/abs/2407.03263
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 horizontal objects, leaving multi-oriented objects common in aerial image
Externí odkaz:
http://arxiv.org/abs/2407.01016
The sparsely activated mixture of experts (MoE) model presents a promising alternative to traditional densely activated (dense) models, enhancing both quality and computational efficiency. However, training MoE models from scratch demands extensive d
Externí odkaz:
http://arxiv.org/abs/2406.04801
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 Anomaly Detection by Adapting a pre-trained CLIP model. To this end, we
Externí odkaz:
http://arxiv.org/abs/2403.09493
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is inefficient as it
Externí odkaz:
http://arxiv.org/abs/2403.01439
Autor:
Yang, Hongcheng, Liang, Dingkang, Zhang, Dingyuan, Liu, Zhe, Zou, Zhikang, Jiang, Xingyu, Zhu, Yingying
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 a challenging problem, such that efficient downsampling methods play
Externí odkaz:
http://arxiv.org/abs/2402.17521
Autor:
Liang, Dingkang, Zhou, Xin, Xu, Wei, Zhu, Xingkui, Zou, Zhikang, Ye, Xiaoqing, Tan, Xiao, Bai, Xiang
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 quadratic complexity, making the design of a linear complexity method wi
Externí odkaz:
http://arxiv.org/abs/2402.10739
Autor:
Xiong, Kaixin, Zhang, Dingyuan, Liang, Dingkang, Liu, Zhe, Yang, Hongcheng, Dikubab, Wondimu, Cheng, Jianwei, Bai, Xiang
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 information. Most existing image-based methods infer objects' location in
Externí odkaz:
http://arxiv.org/abs/2401.15319
Defect detection is a critical research area in artificial intelligence. Recently, synthetic data-based self-supervised learning has shown great potential on this task. Although many sophisticated synthesizing strategies exist, little research has be
Externí odkaz:
http://arxiv.org/abs/2310.07585