Zobrazeno 1 - 10
of 733
pro vyhledávání: '"Barnes, Nick"'
Autor:
Cui, Ruikai, Song, Xibin, Sun, Weixuan, Wang, Senbo, Liu, Weizhe, Chen, Shenzhou, Shang, Taizhang, Li, Yang, Barnes, Nick, Li, Hongdong, Ji, Pan
Large Reconstruction Models have made significant strides in the realm of automated 3D content generation from single or multiple input images. Despite their success, these models often produce 3D meshes with geometric inaccuracies, stemming from the
Externí odkaz:
http://arxiv.org/abs/2405.15622
Existing eye fixation prediction methods perform the mapping from input images to the corresponding dense fixation maps generated from raw fixation points. However, due to the stochastic nature of human fixation, the generated dense fixation maps may
Externí odkaz:
http://arxiv.org/abs/2403.14821
Autor:
Sun, Weixuan, Zhang, Yanhao, Qin, Zhen, Liu, Zheyuan, Cheng, Lin, Wang, Fanyi, Zhong, Yiran, Barnes, Nick
In this work, we propose a new transformer-based regularization to better localize objects for Weakly supervised semantic segmentation (WSSS). In image-level WSSS, Class Activation Map (CAM) is adopted to generate object localization as pseudo segmen
Externí odkaz:
http://arxiv.org/abs/2308.04321
We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and FGSM, do
Externí odkaz:
http://arxiv.org/abs/2307.16572
Point cloud completion aims to recover the complete shape based on a partial observation. Existing methods require either complete point clouds or multiple partial observations of the same object for learning. In contrast to previous approaches, we p
Externí odkaz:
http://arxiv.org/abs/2307.14726
For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary classific
Externí odkaz:
http://arxiv.org/abs/2307.13539
Effectively measuring and modeling the reliability of a trained model is essential to the real-world deployment of monocular depth estimation (MDE) models. However, the intrinsic ill-posedness and ordinal-sensitive nature of MDE pose major challenges
Externí odkaz:
http://arxiv.org/abs/2307.09929
Autor:
Naveed, Humza, Khan, Asad Ullah, Qiu, Shi, Saqib, Muhammad, Anwar, Saeed, Usman, Muhammad, Akhtar, Naveed, Barnes, Nick, Mian, Ajmal
Large Language Models (LLMs) have recently demonstrated remarkable capabilities in natural language processing tasks and beyond. This success of LLMs has led to a large influx of research contributions in this direction. These works encompass diverse
Externí odkaz:
http://arxiv.org/abs/2307.06435
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level se
Externí odkaz:
http://arxiv.org/abs/2307.03376
Publikováno v:
Machine Intelligence Research (2024)
Unlike existing fully-supervised approaches, we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach. We leverage the ability of masked autoencoders -- self-superv
Externí odkaz:
http://arxiv.org/abs/2306.07792