Search Results for author: Sangdoo Yun

Found 50 papers, 37 papers with code

ProPILE: Probing Privacy Leakage in Large Language Models

no code implementations4 Jul 2023 Siwon Kim, Sangdoo Yun, Hwaran Lee, Martin Gubri, Sungroh Yoon, Seong Joon Oh

The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PII).

Augmenting Sub-model to Improve Main Model

1 code implementation20 Jun 2023 Byeongho Heo, Taekyung Kim, Sangdoo Yun, Dongyoon Han

While the main model employs conventional training recipes, the sub-model leverages the benefit of additional regularization.

Self-Supervised Image Classification Transfer Learning

MPCHAT: Towards Multimodal Persona-Grounded Conversation

1 code implementation27 May 2023 Jaewoo Ahn, Yeda Song, Sangdoo Yun, Gunhee Kim

In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities.

Speaker Identification

Who Wrote this Code? Watermarking for Code Generation

no code implementations24 May 2023 Taehyun Lee, Seokhee Hong, Jaewoo Ahn, Ilgee Hong, Hwaran Lee, Sangdoo Yun, Jamin Shin, Gunhee Kim

Large language models for code have recently shown remarkable performance in generating executable code.

Code Generation Text Detection

What Do Self-Supervised Vision Transformers Learn?

1 code implementation1 May 2023 Namuk Park, Wonjae Kim, Byeongho Heo, Taekyung Kim, Sangdoo Yun

We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks.

Contrastive Learning

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

Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts

2 code implementations30 Mar 2023 Dongyoon Han, Junsuk Choe, Seonghyeok Chun, John Joon Young Chung, Minsuk Chang, Sangdoo Yun, Jean Y. Song, Seong Joon Oh

We refer to the new paradigm of training models with annotation byproducts as learning using annotation byproducts (LUAB).

Time Series

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 implementation20 Mar 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

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

no code implementations29 Jan 2023 Jang-Hyun Kim, Sangdoo Yun, Hyun Oh Song

In this paper, we propose a unified approach for identifying the problematic data by utilizing a largely ignored source of information: a relational structure of data in the feature-embedded space.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

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

Exploring Temporally Dynamic Data Augmentation for Video Recognition

no code implementations30 Jun 2022 Taeoh Kim, Jinhyung Kim, Minho Shim, Sangdoo Yun, Myunggu Kang, Dongyoon Wee, Sangyoun Lee

The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations.

Action Segmentation Image Augmentation +3

Dataset Condensation via Efficient Synthetic-Data Parameterization

2 code implementations30 May 2022 Jang-Hyun Kim, Jinuk Kim, Seong Joon Oh, Sangdoo Yun, Hwanjun Song, JoonHyun Jeong, Jung-Woo Ha, Hyun Oh Song

The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.

Dataset Condensation

Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

1 code implementation CVPR 2022 Jungbeom Lee, Seong Joon Oh, Sangdoo Yun, Junsuk Choe, Eunji Kim, Sungroh Yoon

However, training on class labels only, classifiers suffer from the spurious correlation between foreground and background cues (e. g. train and rail), fundamentally bounding the performance of WSSS.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

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

Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning

1 code implementation CVPR 2022 Jongin Lim, Sangdoo Yun, Seulki Park, Jin Young Choi

In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling.

Metric Learning Node Classification

OCR-free Document Understanding Transformer

3 code implementations30 Nov 2021 Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park

Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.

Document Image Classification Optical Character Recognition +1

Observations on K-image Expansion of Image-Mixing Augmentation for Classification

no code implementations8 Oct 2021 JoonHyun Jeong, Sungmin Cha, Youngjoon Yoo, Sangdoo Yun, Taesup Moon, Jongwon Choi

Image-mixing augmentations (e. g., Mixup and CutMix), which typically involve mixing two images, have become the de-facto training techniques for image classification.

Adversarial Robustness Classification +1

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.

Progressive Transmission and Inference of Deep Learning Models

1 code implementation3 Oct 2021 Youngsoo Lee, Sangdoo Yun, Yeonghun Kim, Sunghee Choi

On the server-side, a deep learning model is divided and progressively transmitted to the user devices.

Normalization Matters in Weakly Supervised Object Localization

1 code implementation ICCV 2021 Jeesoo Kim, Junsuk Choe, Sangdoo Yun, Nojun Kwak

Weakly-supervised object localization (WSOL) enables finding an object using a dataset without any localization information.

Weakly-Supervised Object Localization

Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels

no code implementations14 Jun 2021 Seulki Park, Hwanjun Song, Daeho Um, Dae Ung Jo, Sangdoo Yun, Jin Young Choi

Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model.

Learning with noisy labels

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

VideoMix: Rethinking Data Augmentation for Video Classification

2 code implementations7 Dec 2020 Sangdoo Yun, Seong Joon Oh, Byeongho Heo, Dongyoon Han, Jinhyung Kim

Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers.

Action Localization Action Recognition +5

Rethinking Channel Dimensions for Efficient Model Design

10 code implementations CVPR 2021 Dongyoon Han, Sangdoo Yun, Byeongho Heo, Youngjoon Yoo

We then investigate the channel configuration of a model by searching network architectures concerning the channel configuration under the computational cost restriction.

Image Classification Instance Segmentation +4

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

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

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.

Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold

no code implementations CVPR 2017 YoungJoon Yoo, Sangdoo Yun, Hyung Jin Chang, Yiannis Demiris, Jin Young Choi

(iii) The proposed regression is embedded into a generative model, and the whole procedure is developed by the variational autoencoder framework.


EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse

2 code implementations15 Jun 2019 YoungJoon Yoo, Dongyoon Han, Sangdoo Yun

In this paper, we propose a new multi-scale face detector having an extremely tiny number of parameters (EXTD), less than 0. 1 million, as well as achieving comparable performance to deep heavy detectors.

Face Detection

A Comprehensive Overhaul of Feature Distillation

2 code implementations ICCV 2019 Byeongho Heo, Jeesoo Kim, Sangdoo Yun, Hyojin Park, Nojun Kwak, Jin Young Choi

We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function.

General Classification Image Classification +4

Character Region Awareness for Text Detection

18 code implementations CVPR 2019 Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee

Scene text detection methods based on neural networks have emerged recently and have shown promising results.

 Ranked #1 on Scene Text Detection on ICDAR 2013 (Precision metric)

Scene Text Detection Text Detection

C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation

2 code implementations12 Dec 2018 Hyojin Park, Youngjoon Yoo, Geonseok Seo, Dongyoon Han, Sangdoo Yun, Nojun Kwak

To resolve this problem, we propose a new block called Concentrated-Comprehensive Convolution (C3) which applies the asymmetric convolutions before the depth-wise separable dilated convolution to compensate for the information loss due to dilated convolution.

Semantic Segmentation

Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

2 code implementations8 Nov 2018 Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi

In this paper, we propose a knowledge transfer method via distillation of activation boundaries formed by hidden neurons.

Transfer Learning

Knowledge Distillation with Adversarial Samples Supporting Decision Boundary

1 code implementation15 May 2018 Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi

In this paper, we provide a new perspective based on a decision boundary, which is one of the most important component of a classifier.

Adversarial Attack Knowledge Distillation

Context-aware Deep Feature Compression for High-speed Visual Tracking

1 code implementation CVPR 2018 Jongwon Choi, Hyung Jin Chang, Tobias Fischer, Sangdoo Yun, Kyuewang Lee, Jiyeoup Jeong, Yiannis Demiris, Jin Young Choi

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers.

Denoising Feature Compression +3

Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation

no code implementations27 Nov 2017 YoungJoon Yoo, SeongUk Park, Junyoung Choi, Sangdoo Yun, Nojun Kwak

In addition to this performance enhancement problem, we show that the proposed PGN can be adopted to solve the classical adversarial problem without utilizing the information on the target classifier.

Classification General Classification

Attentional Correlation Filter Network for Adaptive Visual Tracking

1 code implementation IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017 Jongwon Choi, Hyung Jin Chang, Sangdoo Yun, Tobias Fischer, Yiannis Demiris, Jin Young Choi

We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency.

Visual Object Tracking Visual Tracking

Palettenet: Image recolorization with given color palette

1 code implementation The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2017 Junho Cho, Sangdoo Yun, Kyoung Mu Lee, Jin Young Choi

PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette.

Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning

1 code implementation CVPR 2017 Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi

In contrast to the existing trackers using deep networks, the proposed tracker is designed to achieve a light computation as well as satisfactory tracking accuracy in both location and scale.

reinforcement-learning Reinforcement Learning (RL) +1

Unsupervised Holistic Image Generation from Key Local Patches

1 code implementation ECCV 2018 Donghoon Lee, Sangdoo Yun, Sungjoon Choi, Hwiyeon Yoo, Ming-Hsuan Yang, Songhwai Oh

We introduce a new problem of generating an image based on a small number of key local patches without any geometric prior.

Image Generation

Visual Path Prediction in Complex Scenes With Crowded Moving Objects

no code implementations CVPR 2016 YoungJoon Yoo, Kimin Yun, Sangdoo Yun, JongHee Hong, Hawook Jeong, Jin Young Choi

In this paper, we consider moving dynamics of co-occurring objects for path prediction in a scene that includes crowded moving objects.

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