Zobrazeno 1 - 10
of 339
pro vyhledávání: '"Li, Xueqian"'
The training of vision transformer (ViT) networks on small-scale datasets poses a significant challenge. By contrast, convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on such problems. In this pa
Externí odkaz:
http://arxiv.org/abs/2404.01139
Autor:
Liu, Dongrui, Liu, Daqi, Li, Xueqian, Lin, Sihao, xie, Hongwei, Wang, Bing, Chang, Xiaojun, Chu, Lei
Neural Scene Flow Prior (NSFP) and Fast Neural Scene Flow (FNSF) have shown remarkable adaptability in the context of large out-of-distribution autonomous driving. Despite their success, the underlying reasons for their astonishing generalization cap
Externí odkaz:
http://arxiv.org/abs/2403.16116
Autor:
Li, Xueqian, Lucey, Simon
In contrast to current state-of-the-art methods, such as NSFP [25], which employ deep implicit neural functions for modeling scene flow, we present a novel approach that utilizes classical kernel representations. This representation enables our appro
Externí odkaz:
http://arxiv.org/abs/2403.05896
Training vision transformer networks on small datasets poses challenges. In contrast, convolutional neural networks (CNNs) can achieve state-of-the-art performance by leveraging their architectural inductive bias. In this paper, we investigate whethe
Externí odkaz:
http://arxiv.org/abs/2401.12511
The test-time optimization of scene flow - using a coordinate network as a neural prior - has gained popularity due to its simplicity, lack of dataset bias, and state-of-the-art performance. We observe, however, that although coordinate networks capt
Externí odkaz:
http://arxiv.org/abs/2310.10301
End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment. Methods like PointNet, or the more recent point cloud transformer -- and its variants -- all employ
Externí odkaz:
http://arxiv.org/abs/2309.00339
Neural Scene Flow Prior (NSFP) is of significant interest to the vision community due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with dense lidar points. The approach utilizes a coordinate neural network t
Externí odkaz:
http://arxiv.org/abs/2304.09121
It is well noted that coordinate-based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features. Hitherto, the rationale for the effectiveness of these positiona
Externí odkaz:
http://arxiv.org/abs/2205.08987
Autor:
Wang, Kuiyou, Huang, Kexin, Li, Xueqian, Wu, Hao, Wang, Li, Bai, Fengyu, Tan, Mingqian, Su, Wentao
Publikováno v:
In Food Chemistry 1 February 2025 464 Part 1
Before the deep learning revolution, many perception algorithms were based on runtime optimization in conjunction with a strong prior/regularization penalty. A prime example of this in computer vision is optical and scene flow. Supervised learning ha
Externí odkaz:
http://arxiv.org/abs/2111.01253