Search Results for author:
Found 4 papers, 3 papers with code
DTBS: Dual-Teacher Bi-directional Self-training for Domain Adaptation in Nighttime Semantic Segmentation
Because the one-directional knowledge transfer from a single teacher is insufficient to adapt to a large domain shift.
PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry
Different from previous methods that only use geometry representation, our module is specifically designed to effectively correlate color into geometry for the point cloud registration task.
PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration
Recently, it has achieved huge success in incorporating Transformer into point cloud feature representation, which usually adopts a self-attention module to learn intra-point-cloud features first, then utilizes a cross-attention module to perform feature exchange between input point clouds.
Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation
In this paper, we propose a novel self-supervised learning framework for volumetric medical images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
