CoLLiS performs single-step collaborative training of multiple LiDAR representations with adaptive multi-source distillation and online inter-student disparity monitoring to mitigate confirmation bias in semi-supervised semantic segmentation.
An image is worth 16x16 words: Transformers for image recognition at scale
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Collaborative Learning for Semi-Supervised LiDAR Semantic Segmentation
CoLLiS performs single-step collaborative training of multiple LiDAR representations with adaptive multi-source distillation and online inter-student disparity monitoring to mitigate confirmation bias in semi-supervised semantic segmentation.