Tag: robustness

A new composite scoring framework called RECAF jointly measures deepfake detectors' accuracy, robustness to image distortions, and cross-dataset generalization, revealing ...

Researchers in China have developed a dual-path deep learning network that keeps multimodal sentiment analysis accurate even when text, audio ...

Researchers have recast multi-label classification as an order structure learning problem, yielding classifiers that better withstand noisy and imbalanced labels ...

Researchers have developed an offline-to-online reinforcement learning framework that uses adversarial action perturbations and an adaptive curriculum to make robot ...