Search Results for author: Sanghyuk Chun

Found 40 papers, 28 papers with code

Improved Probabilistic Image-Text Representations

1 code implementation29 May 2023 Sanghyuk Chun

In addition, two optimization techniques are proposed to enhance PCME++ further; first, the incorporation of pseudo-positives to prevent the loss saturation problem under massive false negatives; second, mixed sample data augmentation for probabilistic matching.

Data Augmentation Image-text matching +2

Three Recipes for Better 3D Pseudo-GTs of 3D Human Mesh Estimation in the Wild

1 code implementation10 Apr 2023 Gyeongsik Moon, Hongsuk Choi, Sanghyuk Chun, Jiyoung Lee, Sangdoo Yun

Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs).

3D Multi-Person Pose Estimation

CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion

1 code implementation21 Mar 2023 Geonmo Gu, Sanghyuk Chun, Wonjae Kim, HeeJae Jun, Yoohoon Kang, Sangdoo Yun

This paper proposes a novel diffusion-based model, CompoDiff, for solving Composed Image Retrieval (CIR) with latent diffusion and presents a newly created dataset of 18 million reference images, conditions, and corresponding target image triplets to train the model.

Composed Image Retrieval (CoIR) Retrieval

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

1 code implementation ICCV 2023 Song Park, Sanghyuk Chun, Byeongho Heo, Wonjae Kim, Sangdoo Yun

We need billion-scale images to achieve more generalizable and ground-breaking vision models, as well as massive dataset storage to ship the images (e. g., the LAION-4B dataset needs 240TB storage space).

Continual Learning

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

no code implementations1 Mar 2023 Sangwon Jung, TaeEon Park, Sanghyuk Chun, Taesup Moon

Many existing group fairness-aware training methods aim to achieve the group fairness by either re-weighting underrepresented groups based on certain rules or using weakly approximated surrogates for the fairness metrics in the objective as regularization terms.


Group Generalized Mean Pooling for Vision Transformer

no code implementations8 Dec 2022 Byungsoo Ko, Han-Gyu Kim, Byeongho Heo, Sangdoo Yun, Sanghyuk Chun, Geonmo Gu, Wonjae Kim

As ViT groups the channels via a multi-head attention mechanism, grouping the channels by GGeM leads to lower head-wise dependence while amplifying important channels on the activation maps.

Image Retrieval Representation Learning +1

A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective

1 code implementation21 Aug 2022 Chanwoo Park, Sangdoo Yun, Sanghyuk Chun

Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level regularization of the underlying training loss and a regularization of the first layer parameters.

Adversarial Robustness Data Augmentation

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

1 code implementation21 Mar 2022 Junbum Cha, Kyungjae Lee, Sungrae Park, Sanghyuk Chun

Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains.

Domain Generalization

Dataset Condensation with Contrastive Signals

2 code implementations7 Feb 2022 Saehyung Lee, Sanghyuk Chun, Sangwon Jung, Sangdoo Yun, Sungroh Yoon

However, in this study, we prove that the existing DC methods can perform worse than the random selection method when task-irrelevant information forms a significant part of the training dataset.

Continual Learning Dataset Condensation +1

Few-shot Font Generation with Weakly Supervised Localized Representations

2 code implementations22 Dec 2021 Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim

Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style.

Font Generation

Learning Fair Classifiers with Partially Annotated Group Labels

1 code implementation CVPR 2022 Sangwon Jung, Sanghyuk Chun, Taesup Moon

To address this problem, we propose a simple Confidence-based Group Label assignment (CGL) strategy that is readily applicable to any fairness-aware learning method.


Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective

no code implementations ICLR 2022 Luca Scimeca, Seong Joon Oh, Sanghyuk Chun, Michael Poli, Sangdoo Yun

This phenomenon, also known as shortcut learning, is emerging as a key limitation of the current generation of machine learning models.

Biased Multi-Domain Adversarial Training

no code implementations29 Sep 2021 Saehyung Lee, Hyungyu Lee, Sanghyuk Chun, Sungroh Yoon

Several recent studies have shown that the use of extra in-distribution data can lead to a high level of adversarial robustness.

Adversarial Robustness

StyleAugment: Learning Texture De-biased Representations by Style Augmentation without Pre-defined Textures

no code implementations24 Aug 2021 Sanghyuk Chun, Song Park

Hence, StyleAugment let the model observe abundant confounding cues for each image by on-the-fly the augmentation strategy, while the augmented images are more realistic than artistic style transferred images.

Data Augmentation Style Transfer

Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

no code implementations NeurIPS 2021 Michael Poli, Stefano Massaroli, Luca Scimeca, Seong Joon Oh, Sanghyuk Chun, Atsushi Yamashita, Hajime Asama, Jinkyoo Park, Animesh Garg

Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes.

Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts

4 code implementations ICCV 2021 Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim

MX-Font extracts multiple style features not explicitly conditioned on component labels, but automatically by multiple experts to represent different local concepts, e. g., left-side sub-glyph.

Disentanglement Font Generation +1

Rethinking Spatial Dimensions of Vision Transformers

10 code implementations ICCV 2021 Byeongho Heo, Sangdoo Yun, Dongyoon Han, Sanghyuk Chun, Junsuk Choe, Seong Joon Oh

We empirically show that such a spatial dimension reduction is beneficial to a transformer architecture as well, and propose a novel Pooling-based Vision Transformer (PiT) upon the original ViT model.

Dimensionality Reduction Image Classification +2

Probabilistic Embeddings for Cross-Modal Retrieval

1 code implementation CVPR 2021 Sanghyuk Chun, Seong Joon Oh, Rafael Sampaio de Rezende, Yannis Kalantidis, Diane Larlus

Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space.

Cross-Modal Retrieval Retrieval

Few-shot Font Generation with Localized Style Representations and Factorization

3 code implementations23 Sep 2020 Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim

However, learning component-wise styles solely from reference glyphs is infeasible in the few-shot font generation scenario, when a target script has a large number of components, e. g., over 200 for Chinese.

Font Generation

Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets

2 code implementations8 Jul 2020 Junsuk Choe, Seong Joon Oh, Sanghyuk Chun, Seungho Lee, Zeynep Akata, Hyunjung Shim

In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.

Few-Shot Learning Model Selection +1

AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights

4 code implementations ICLR 2021 Byeongho Heo, Sanghyuk Chun, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha

Because of the scale invariance, this modification only alters the effective step sizes without changing the effective update directions, thus enjoying the original convergence properties of GD optimizers.

Audio Classification Image Classification +3

Few-shot Compositional Font Generation with Dual Memory

3 code implementations ECCV 2020 Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, Hwalsuk Lee

By utilizing the compositionality of compositional scripts, we propose a novel font generation framework, named Dual Memory-augmented Font Generation Network (DM-Font), which enables us to generate a high-quality font library with only a few samples.

Font Generation

An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods

no code implementations9 Mar 2020 Sanghyuk Chun, Seong Joon Oh, Sangdoo Yun, Dongyoon Han, Junsuk Choe, Youngjoon Yoo

Despite apparent human-level performances of deep neural networks (DNN), they behave fundamentally differently from humans.

Bayesian Inference

Evaluating Weakly Supervised Object Localization Methods Right

2 code implementations CVPR 2020 Junsuk Choe, Seong Joon Oh, Seungho Lee, Sanghyuk Chun, Zeynep Akata, Hyunjung Shim

In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.

Few-Shot Learning Model Selection +1

Visualizing and Understanding Self-attention based Music Tagging

no code implementations11 Nov 2019 Minz Won, Sanghyuk Chun, Xavier Serra

Recently, we proposed a self-attention based music tagging model.

Sound Audio and Speech Processing

Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling

no code implementations15 Oct 2019 YoungJoon Yoo, Sanghyuk Chun, Sangdoo Yun, Jung-Woo Ha, Jaejun Yoo

We first assume that the priors of future samples can be generated in an independently and identically distributed (i. i. d.)

Learning De-biased Representations with Biased Representations

3 code implementations ICML 2020 Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, Seong Joon Oh

This tactic is feasible in many scenarios where it is much easier to define a set of biased representations than to define and quantify bias.

Toward Interpretable Music Tagging with Self-Attention

2 code implementations12 Jun 2019 Minz Won, Sanghyuk Chun, Xavier Serra

In addition, we demonstrate the interpretability of the proposed architecture with a heat map visualization.

Sound Audio and Speech Processing

Multi-Domain Processing via Hybrid Denoising Networks for Speech Enhancement

1 code implementation21 Dec 2018 Jang-Hyun Kim, Jaejun Yoo, Sanghyuk Chun, Adrian Kim, Jung-Woo Ha

We present a hybrid framework that leverages the trade-off between temporal and frequency precision in audio representations to improve the performance of speech enhancement task.

Audio and Speech Processing Sound

Scalable Iterative Algorithm for Robust Subspace Clustering

no code implementations5 Mar 2015 Sanghyuk Chun, Yung-Kyun Noh, Jinwoo Shin

Subspace clustering (SC) is a popular method for dimensionality reduction of high-dimensional data, where it generalizes Principal Component Analysis (PCA).

Clustering Dimensionality Reduction

Cannot find the paper you are looking for? You can Submit a new open access paper.