Zobrazeno 1 - 10
of 793
pro vyhledávání: '"Fan, Deng"'
Camouflaged Object Detection (COD) aims to detect objects with camouflaged properties. Although previous studies have focused on natural (animals and insects) and unnatural (artistic and synthetic) camouflage detection, plant camouflage has been negl
Externí odkaz:
http://arxiv.org/abs/2410.17598
Autor:
Ji, Ge-Peng, Liu, Jingyi, Xu, Peng, Barnes, Nick, Khan, Fahad Shahbaz, Khan, Salman, Fan, Deng-Ping
Colonoscopy is currently one of the most sensitive screening methods for colorectal cancer. This study investigates the frontiers of intelligent colonoscopy techniques and their prospective implications for multimodal medical applications. With this
Externí odkaz:
http://arxiv.org/abs/2410.17241
Autor:
Sun, Yasheng, Li, Bohan, Zhuge, Mingchen, Fan, Deng-Ping, Khan, Salman, Khan, Fahad Shahbaz, Koike, Hideki
Recent breakthroughs in understanding the human brain have revealed its impressive ability to efficiently process and interpret human thoughts, opening up possibilities for intervening in brain signals. In this paper, we aim to develop a straightforw
Externí odkaz:
http://arxiv.org/abs/2408.07317
Autor:
Gong, Cheng, Zheng, Haoshuai, Hu, Mengting, Lin, Zheng, Fan, Deng-Ping, Zhang, Yuzhi, Li, Tao
Publikováno v:
CAAI Artificial Intelligence Research, 2024
Quantization is a promising method that reduces memory usage and computational intensity of Deep Neural Networks (DNNs), but it often leads to significant output error that hinder model deployment. In this paper, we propose Bias Compensation (BC) to
Externí odkaz:
http://arxiv.org/abs/2404.01892
LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion
Autor:
Zhao, Pancheng, Xu, Peng, Qin, Pengda, Fan, Deng-Ping, Zhang, Zhicheng, Jia, Guoli, Zhou, Bowen, Yang, Jufeng
Camouflaged vision perception is an important vision task with numerous practical applications. Due to the expensive collection and labeling costs, this community struggles with a major bottleneck that the species category of its datasets is limited
Externí odkaz:
http://arxiv.org/abs/2404.00292
Estimating reliable geometric model parameters from the data with severe outliers is a fundamental and important task in computer vision. This paper attempts to sample high-quality subsets and select model instances to estimate parameters in the mult
Externí odkaz:
http://arxiv.org/abs/2403.06444
Autor:
Jiang, Yao, Yan, Xinyu, Ji, Ge-Peng, Fu, Keren, Sun, Meijun, Xiong, Huan, Fan, Deng-Ping, Khan, Fahad Shahbaz
Publikováno v:
Visual Intelligence, 2024, Vol. 2, article no. 17
The advent of large vision-language models (LVLMs) represents a remarkable advance in the quest for artificial general intelligence. However, the model's effectiveness in both specialized and general tasks warrants further investigation. This paper e
Externí odkaz:
http://arxiv.org/abs/2403.04306
The estimation of implicit cross-frame correspondences and the high computational cost have long been major challenges in video semantic segmentation (VSS) for driving scenes. Prior works utilize keyframes, feature propagation, or cross-frame attenti
Externí odkaz:
http://arxiv.org/abs/2401.15261
Autor:
Zheng, Peng, Gao, Dehong, Fan, Deng-Ping, Liu, Li, Laaksonen, Jorma, Ouyang, Wanli, Sebe, Nicu
We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral
Externí odkaz:
http://arxiv.org/abs/2401.03407
In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. Previous
Externí odkaz:
http://arxiv.org/abs/2401.02317