Deep Learning
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Furthermore, we propose a dual-policy control framework, where a kinematic policy and an RFC-based policy work in tandem to synthesize multi-modal infinite-horizon human motions without any task guidance or user input.
Efficient Combination of Rematerialization and Offloading for Training DNNs
Rematerialization and offloading are two well known strategies to save memory during the training phase of deep neural networks, allowing data scientists to consider larger models, batch sizes or higher resolution data.
Efficient Training of Visual Transformers with Small Datasets
Our task is used jointly with the standard (supervised) training and it does not depend on specific architectural choices, thus it can be easily plugged in the existing VTs.
Disentangling the Predictive Variance of Deep Ensembles through the Neural Tangent Kernel
Principled mechanisms for uncertainty quantification would rely on Bayesian inference with an appropriate prior.
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation Ping Hu1 Stan Sclaroff 1 Kate Saenko 1, 2 1 Boston University 2
Though achieving promising results, these methods may still suffer from several limitations.
AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
Recent studies have shown that the performance of forgery detection can be improved with diverse and challenging Deepfakes datasets.
Strongly Incremental Constituency Parsing with Graph Neural Networks
Parsing sentences into syntax trees can benefit downstream applications in NLP . Transition-based parsers build trees by executing actions in a state transition system.