RadProPoser uses a variational encoder-decoder with spectral attention to predict 3D poses and aleatoric uncertainties from radar tensors, achieving 6.425 cm MPJPE on a new benchmark and 5.042 cm on HuPR with calibrated uncertainties.
A structured review of literature on uncertainty in machine learning & deep learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
AEGIS combines SemantiGAN filtering with evidential learning on five handcrafted instability metrics to detect adversarial attacks, reporting 92.1% AUROC on Tiny ImageNet across six attack types.
citing papers explorer
-
RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits
RadProPoser uses a variational encoder-decoder with spectral attention to predict 3D poses and aleatoric uncertainties from radar tensors, achieving 6.425 cm MPJPE on a new benchmark and 5.042 cm on HuPR with calibrated uncertainties.
-
VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning
VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.
-
AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors
AEGIS combines SemantiGAN filtering with evidential learning on five handcrafted instability metrics to detect adversarial attacks, reporting 92.1% AUROC on Tiny ImageNet across six attack types.