Search Results for author:
Found 5 papers, 4 papers with code
Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Oobleck enables resilient distributed training of large DNN models with guaranteed fault tolerance.
Chasing Low-Carbon Electricity for Practical and Sustainable DNN Training
Specifically, our solution observes real-time carbon intensity shifts during training and controls the energy consumption of GPUs, thereby reducing carbon footprint while maintaining training performance.
SLRNet: Semi-Supervised Semantic Segmentation Via Label Reuse for Human Decomposition Images
We evaluate our method on a large dataset of human decomposition images and find that our method, while conceptually simple, outperforms state-of-the-art consistency and pseudo-labeling-based methods for the segmentation of this dataset.
Pseudo Pixel-level Labeling for Images with Evolving Content
Annotating images for semantic segmentation requires intense manual labor and is a time-consuming and expensive task especially for domains with a scarcity of experts, such as Forensic Anthropology.
Conditional Gaussian Distribution Learning for Open Set Recognition
A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes.
