Xiong Zhou

Variation-Bounded Losses for Learning with Noisy Labels

Deep Denoising Prior: You Only Need a Deep Gaussian Denoiser

Neural Field Classifiers via Target Encoding and Classification Loss

Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data

Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs

$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise

Contraction and Alienation: Towards Theoretical Understanding of Non-Contrastive Learning with Neighbor-Averaging Dynamics

GM-DDPM: Denoising diffusion probabilistic models with Gaussian Mixture Noise

Everyone Counts: Fair and Accurate Heterogeneous Federated Learning with Resource-Adaptive Model Modulation

Communication-Efficient Federated Learning via Gradient Distillation