Earlier work demonstrates the promise of deeplearning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeSegV2 that is more robust to dropout noise in LiDAR point clouds. With improved model structure, training loss, batch normalization and additional input channel, SqueezeSegV2 achieves significant accuracy improvement when trained on real data. Training models for point cloud segmentation requires large amounts of labeled point-cloud data, which is expensive to obtain. To sidestep the cost of collection and annotation, simulators such as GTA-V can be used to create unlimited amounts of labeled, synthetic data. However, due to domain shift, models trained on synthetic data often do not generalize well to the real world. We address this problem with a domainadaptation training pipeline consisting of three major components: 1) learned intensity rendering, 2) geodesic correlation alignment, and 3) progressive domain calibration. When trained on real data, our new model exhibits segmentation accuracy improvements of 6.0-8.6% over the original SqueezeSeg. When training our new model on synthetic data using the proposed domain adaptation pipeline, we nearly double test accuracy on real-world data, from 29.0% to 57.4%. Our source code and synthetic dataset will be open-sourced.
The China Jinping Underground Laboratory (CJPL), which has the lowest cosmic-ray muon flux and the lowest reactor neutrino flux of any laboratory, is ideal to carry out low-energy neutrino experiments. With two detectors and a total fiducial mass of 2000 tons for solar neutrino physics (equivalently, 3000 tons for geo-neutrino and supernova neutrino physics), the Jinping neutrino experiment will have the potential to identify the neutrinos from the CNO fusion cycles of the Sun, to cover the transition phase for the solar neutrino oscillation from vacuum to matter mixing, and to measure the geo-neutrino flux, including the Th/U ratio. These goals can be fulfilled with mature existing techniques. Efforts on increasing the target mass with multi-modular neutrino detectors and on developing the slow liquid scintillator will increase the Jinping discovery potential in the study of solar neutrinos, geo-neutrinos, supernova neutrinos, and dark matter.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.