5 papers
Keep the Core: Adversarial Priors for Significance-Preserving Brain MRI Segmentation
Feifei Zhang, Zhenhong Jia, Sensen Song +3
Medical image segmentation is constrained by sparse pathological annotations. Existing augmentation strategies, from conventional transforms to random masking for self-supervision,…
Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM
Shouhe Zhang, Dayong Ren, Sensen Song +2
Extreme exposure degrades both the 3D map reconstruction and semantic segmentation accuracy, which is particularly detrimental to tightly-coupled systems. To achieve illumination i…
Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation
Feifei Zhang, Zhenhong Jia, Sensen Song +2
Despite the remarkable success of the end-to-end paradigm in deep learning, it often suffers from slow convergence and heavy reliance on large-scale datasets, which fundamentally l…
Minkowski-MambaNet: A Point Cloud Framework with Selective State Space Models for Forest Biomass Quantification
Jinxiang Tu, Dayong Ren, Fei Shi +4
Accurate forest biomass quantification is vital for carbon cycle monitoring. While airborne LiDAR excels at capturing 3D forest structure, directly estimating woody volume and Abov…
ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
Linshuang Diao, Sensen Song, Yurong Qian +1
State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in comp…