1 code implementation • CVPR 2021 • Mingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, Il-Chul Moon
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.
1 code implementation • 10 Jun 2021 • Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon
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)
1 code implementation • NeurIPS 2021 • Hyuck Lee, Seungjae Shin, Heeyoung Kim
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.
2 code implementations • 2 May 2022 • HeeSun Bae, Seungjae Shin, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon
We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels.
1 code implementation • NeurIPS 2023 • DongHyeok Shin, Seungjae Shin, Il-Chul Moon
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.
1 code implementation • 8 Mar 2023 • Seungjae Shin, HeeSun Bae, DongHyeok Shin, Weonyoung Joo, Il-Chul Moon
Training neural networks on a large dataset requires substantial computational costs.
1 code implementation • 9 Jan 2024 • Youngjae Cho, HeeSun Bae, Seungjae Shin, Yeo Dong Youn, Weonyoung Joo, Il-Chul Moon
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.
1 code implementation • 5 Mar 2024 • HeeSun Bae, Seungjae Shin, Byeonghu Na, Il-Chul Moon
We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT.
1 code implementation • 15 Feb 2021 • Dongjun Kim, Kyungwoo Song, Seungjae Shin, Wanmo Kang, Il-Chul Moon, Weonyoung Joo
A simulation is useful when the phenomenon of interest is either expensive to regenerate or irreproducible with the same context.
no code implementations • 4 Mar 2020 • Weonyoung Joo, Dongjun Kim, Seungjae Shin, Il-Chul Moon
Stochastic gradient estimators of discrete random variables are widely explored, for example, Gumbel-Softmax reparameterization trick for Bernoulli and categorical distributions.
no code implementations • 7 Apr 2020 • Seungjae Shin, Kyungwoo Song, JoonHo Jang, Hyemi Kim, Weonyoung Joo, Il-Chul Moon
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.
no code implementations • 13 Apr 2020 • Dongjun Kim, Weonyoung Joo, Seungjae Shin, Kyungwoo Song, Il-Chul Moon
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.
no code implementations • 24 Nov 2020 • Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, Wanmo Kang, Il-Chul Moon
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.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Seungjae Shin, Kyungwoo Song, JoonHo Jang, Hyemi Kim, Weonyoung Joo, Il-Chul Moon
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.
no code implementations • 29 Sep 2021 • Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon
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.
no code implementations • 12 Mar 2024 • Seungjae Shin, HeeSun Bae, Byeonghu Na, Yoon-Yeong Kim, Il-Chul Moon
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.