Search Results for author:
Found 2 papers, 1 papers with code
UpCycling: Semi-supervised 3D Object Detection without Sharing Raw-level Unlabeled Scenes
In this paper, we propose UpCycling, a novel SSL framework for 3D object detection with zero additional raw-level point cloud: learning from unlabeled de-identified intermediate features (i. e., smashed data) to preserve privacy.
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach
By comparing their performance to (bitwidth-dedicated) QAT, existing bitwidth adaptive QAT and vanilla meta-learning, we find that merging bitwidths into meta-learning tasks achieves a higher level of robustness.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
