activity
20232025
most citedUnveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2025

-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Jialiang Wang, Xiong Zhou, Deming Zhai +3

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise…

cs.CV2024

Mesh Denoising Transformer

Wenbo Zhao, Xianming Liu, Deming Zhai +2

Mesh denoising, aimed at removing noise from input meshes while preserving their feature structures, is a practical yet challenging task. Despite the remarkable progress in learnin…

cs.CV2024

SGCNeRF: Few-Shot Neural Rendering via Sparse Geometric Consistency Guidance

Yuru Xiao, Xianming Liu, Deming Zhai +3

Neural Radiance Field (NeRF) technology has made significant strides in creating novel viewpoints. However, its effectiveness is hampered when working with sparsely available views…

cs.CV20241 cited

Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios

Jialei Xu, Xianming Liu, Junjun Jiang +4

Monocular depth estimation from RGB images plays a pivotal role in 3D vision. However, its accuracy can deteriorate in challenging environments such as nighttime or adverse weather…

cs.CV2024

Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning

Chenyang Wang, Junjun Jiang, Xingyu Hu +2

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To addre…

cs.LG2023

On the Dynamics Under the Unhinged Loss and Beyond

Xiong Zhou, Xianming Liu, Hanzhang Wang +3

Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the interm…