Open access
Jul 2026
CANNE: CLIP-Based ANNE Selection for Noisy-Label Learning
Experimental results on CIFAR-10, CIFAR-100, Animal-10N, and Mini-WebVision, together with additional evaluation under open-set noise, show that the proposed CANNE method achieves competitive performance across diverse noisy-label settings.
Ge Jin, Qian Zhang, Li Huang et al.
· Entropy · 0 citations