Search Results for author:
Found 16 papers, 9 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.
Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior
This paper presents a Bayesian-based framework of prompt learning, which could alleviate the overfitting issues on few-shot learning application and increase the adaptability of prompts on unseen instances.
Frequency Domain-based Dataset Distillation
This paper presents FreD, a novel parameterization method for dataset distillation, which utilizes the frequency domain to distill a small-sized synthetic dataset from a large-sized original dataset.
Loss-Curvature Matching for Dataset Selection and Condensation
Training neural networks on a large dataset requires substantial computational costs.
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.
ABC: Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning
The ABC is trained with a class-balanced loss of a minibatch, while using high-quality representations learned from all data points in the minibatch using the backbone SSL algorithm to avoid overfitting and information loss. Moreover, we use consistency regularization, a recent SSL technique for utilizing unlabeled data in a modified way, to train the ABC to be balanced among the classes by selecting unlabeled data with the same probability for each class.
High Precision Score-based Diffusion Models
From the theory side, the difficulty arises in estimating the high precision diffusion because the data score goes to $\infty$ as $t \rightarrow 0$ of the diffusion time.
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
This paper investigates with sufficient empirical evidence that such inverse correlation happens because density estimation is significantly contributed by small diffusion time, whereas sample generation mainly depends on large diffusion time.
Ranked #2 on
Image Generation
on CIFAR-10
(Inception score metric)
Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation
Knowledge distillation is a method of transferring the knowledge from a pretrained complex teacher model to a student model, so a smaller network can replace a large teacher network at the deployment stage.
Neural Posterior Regularization for Likelihood-Free Inference
A simulation is useful when the phenomenon of interest is either expensive to regenerate or irreproducible with the same context.
Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder
Therefore, this paper proposes Disentangled Causal Effect Variational Autoencoder (DCEVAE) to resolve this limitation by disentangling the exogenous uncertainty into two latent variables: either 1) independent to interventions or 2) correlated to interventions without causality.
Neutralizing Gender Bias in Word Embeddings with Latent Disentanglement and Counterfactual Generation
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks.
Adversarial Likelihood-Free Inference on Black-Box Generator
Generative Adversarial Network (GAN) can be viewed as an implicit estimator of a data distribution, and this perspective motivates using the adversarial concept in the true input parameter estimation of black-box generators.
Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation
Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks.
Generalized Gumbel-Softmax Gradient Estimator for Generic Discrete Random Variables
Stochastic gradient estimators of discrete random variables are widely explored, for example, Gumbel-Softmax reparameterization trick for Bernoulli and categorical distributions.
