Search Results for author:
Found 10 papers, 8 papers with code
Unknown Domain Inconsistency Minimization for Domain Generalization
In particular, by aligning the loss landscape acquired in the source domain to the loss landscape of perturbed domains, we expect to achieve generalization grounded on these flat minima for the unknown domains.
Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT.
Training Unbiased Diffusion Models From Biased Dataset
While directly applying it to score-matching is intractable, we discover that using the time-dependent density ratio both for reweighting and score correction can lead to a tractable form of the objective function to regenerate the unbiased data density.
Label-Noise Robust Diffusion Models
This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models.
SAAL: Sharpness-Aware Active Learning
Specifically, our proposed method, Sharpness-Aware Active Learning (SAAL), constructs its acquisition function by selecting unlabeled instances whose perturbed loss becomes maximum.
Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation
Therefore, we propose Unknown-Aware Domain Adversarial Learning (UADAL), which $\textit{aligns}$ the source and the target-$\textit{known}$ distribution while simultaneously $\textit{segregating}$ the target-$\textit{unknown}$ distribution in the feature alignment procedure.
Maximum Likelihood Training of Implicit Nonlinear Diffusion Models
Whereas diverse variations of diffusion models exist, extending the linear diffusion into a nonlinear diffusion process is investigated by very few works.
Ranked #4 on
Image Generation
on CelebA 64x64
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels.
Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features
Furthermore, MATRN stimulates combining semantic features into visual features by hiding visual clues related to the character in the training phase.
Ranked #9 on
Scene Text Recognition
on ICDAR2013
Maximum Likelihood Training of Parametrized Diffusion Model
Specifically, PDM utilizes the flow to non-linearly transform a data variable into a latent variable, and PDM applies the diffusion process to the transformed latent distribution with the linear diffusing mechanism.
