Zobrazeno 1 - 10
of 531
pro vyhledávání: '"Pan, Chunhong"'
We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is realized by exploiting out-of-distribution (OOD) detection to predict whe
Externí odkaz:
http://arxiv.org/abs/2404.00603
Autor:
Zhang, Chenghao, Meng, Gaofeng, Fan, Bin, Tian, Kun, Zhang, Zhaoxiang, Xiang, Shiming, Pan, Chunhong
The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogen
Externí odkaz:
http://arxiv.org/abs/2404.00360
Self-supervised learning (SSL) for RGB images has achieved significant success, yet there is still limited research on SSL for infrared images, primarily due to three prominent challenges: 1) the lack of a suitable large-scale infrared pre-training d
Externí odkaz:
http://arxiv.org/abs/2312.08192
Autor:
Ding, Kun, Wang, Ying, Liu, Pengzhang, Yu, Qiang, Zhang, Haojian, Xiang, Shiming, Pan, Chunhong
Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image recognition compare
Externí odkaz:
http://arxiv.org/abs/2208.13474
Autor:
Nie, Xing, Ni, Bolin, Chang, Jianlong, Meng, Gaomeng, Huo, Chunlei, Zhang, Zhaoxiang, Xiang, Shiming, Tian, Qi, Pan, Chunhong
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and heavily relyin
Externí odkaz:
http://arxiv.org/abs/2207.14381
Autor:
Ding, Kun, Wang, Ying, Liu, Pengzhang, Yu, Qiang, Zhang, Haojian, Xiang, Shiming, Pan, Chunhong
Publikováno v:
In Neurocomputing 28 October 2024 603
Publikováno v:
In Infrared Physics and Technology November 2024 142
Autor:
Nie, Xing, Liu, Yongcheng, Chen, Shaohong, Chang, Jianlong, Huo, Chunlei, Meng, Gaofeng, Tian, Qi, Hu, Weiming, Pan, Chunhong
Exploiting convolutional neural networks for point cloud processing is quite challenging, due to the inherent irregular distribution and discrete shape representation of point clouds. To address these problems, many handcrafted convolution variants h
Externí odkaz:
http://arxiv.org/abs/2108.12856
Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature extraction
Externí odkaz:
http://arxiv.org/abs/2106.13391
In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and detection perform
Externí odkaz:
http://arxiv.org/abs/2101.06438