Safeguarded Dynamic Label Regression for Generalized Noisy Supervision

Understand

Learning with noisy labels, which aims to reduce expensive labors on accurate annotations, has become imperative in the Big Data era.

• Previous noise transition based method has achieved promising results and presented a theoretical guarantee on performance in the case of class-conditional noise.
• However, this type of approaches critically depend on an accurate pre-estimation of the noise transition, which is usually impractical.
• Subsequent improvement adapts the pre-estimation along with the training progress via a Softmax layer.