Search Results for author: Hyunjung Shim

Found 35 papers, 20 papers with code

DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation

1 code implementation16 Jul 2024 Jiwook Kim, Seonho Lee, Jaeyo Shin, Jiho Choi, Hyunjung Shim

However, existing SDS-based 3D editing methods suffer from extensive training time and lead to low-quality results, primarily because these methods deviate from the sampling dynamics of diffusion models.

Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval

no code implementations15 Jul 2024 Youngsun Lim, Hyunjung Shim

Depending on the nature of the hallucination, we employ off-the-shelf image editing tools, either InstructPix2Pix or IP-Adapter, to leverage factual information from the retrieved image.

Common Sense Reasoning Hallucination +3

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

2 code implementations2 Jul 2024 Junsung Park, KyungMin Kim, Hyunjung Shim

Motivated by this issue, we identified key factors of adverse weather and conducted a toy experiment to pinpoint the main causes of performance degradation: (1) Geometric perturbation due to refraction caused by fog or droplets in the air and (2) Point drop due to energy absorption and occlusions.

Data Augmentation LIDAR Semantic Segmentation +2

Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation

1 code implementation28 Jun 2024 Junsung Park, Hyunjung Shim

We further extend our ensemble method to CAMs from AMN (ResNet-like) and MCTformer (ViT-like) models, achieving performance benefits in advanced WSSS models.

Segmentation Weakly-Supervised Semantic Segmentation

Understanding Multi-Granularity for Open-Vocabulary Part Segmentation

1 code implementation17 Jun 2024 Jiho Choi, Seonho Lee, Seungho Lee, Minhyun Lee, Hyunjung Shim

Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities based on diverse and previously unseen vocabularies.

Segmentation

Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing

no code implementations13 Feb 2024 Yunji Jung, Seokju Lee, Tair Djanibekov, Hyunjung Shim, Jong Chul Ye

In this work, we propose a training-free approach for non-rigid editing with Stable Diffusion, aimed at improving the identity preservation quality without compromising editability.

Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels

no code implementations23 Jan 2024 Seungho Lee, Seoungyoon Kang, Hyunjung Shim

This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT).

Language Modelling Segmentation +1

Memory-Efficient Fine-Tuning for Quantized Diffusion Model

no code implementations9 Jan 2024 Hyogon Ryu, Seohyun Lim, Hyunjung Shim

The emergence of billion-parameter diffusion models such as Stable Diffusion XL, Imagen, and DALL-E 3 has significantly propelled the domain of generative AI.

Quantization

Weakly Supervised Semantic Segmentation for Driving Scenes

1 code implementation21 Dec 2023 Dongseob Kim, Seungho Lee, Junsuk Choe, Hyunjung Shim

Notably, the proposed method achieves 51. 8\% mIoU on the Cityscapes test dataset, showcasing its potential as a strong WSSS baseline on driving scene datasets.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

SeiT++: Masked Token Modeling Improves Storage-efficient Training

1 code implementation15 Dec 2023 Minhyun Lee, Song Park, Byeongho Heo, Dongyoon Han, Hyunjung Shim

A recent breakthrough by SeiT proposed the use of Vector-Quantized (VQ) feature vectors (i. e., tokens) as network inputs for vision classification.

Classification Data Augmentation +2

Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data

1 code implementation CVPR 2022 Kyungjune Baek, Hyunjung Shim

Since our synthesizer only considers the generic properties of natural images, the single model pretrained on our dataset can be consistently transferred to various target datasets, and even outperforms the previous methods pretrained with the natural images in terms of Fr'echet inception distance.

Inference Attack Membership Inference Attack +1

S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks

1 code implementation4 Jan 2022 Minjin Choi, jinhong Kim, Joonsek Lee, Hyunjung Shim, Jongwuk Lee

Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user.

Computational Efficiency Session-Based Recommendations

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

Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation

1 code implementation CVPR 2021 Seungho Lee, Minhyun Lee, Jongwuk Lee, Hyunjung Shim

Existing studies in weakly-supervised semantic segmentation (WSSS) using image-level weak supervision have several limitations: sparse object coverage, inaccurate object boundaries, and co-occurring pixels from non-target objects.

Object Saliency Detection +2

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

Session-aware Linear Item-Item Models for Session-based Recommendation

3 code implementations30 Mar 2021 Minjin Choi, jinhong Kim, Joonseok Lee, Hyunjung Shim, Jongwuk Lee

Session-based recommendation aims at predicting the next item given a sequence of previous items consumed in the session, e. g., on e-commerce or multimedia streaming services.

Session-Based Recommendations

Logit As Auxiliary Weak-supervision for More Reliable and Accurate Prediction

no code implementations1 Jan 2021 Duhyeon Bang, Yunho Jeon, Jin-Hwa Kim, Jiwon Kim, Hyunjung Shim

When a person identifies objects, he or she can think by associating objects to many classes and conclude by taking inter-class relations into account.

Data Augmentation

Waste not, Want not: All-Alive Pruning for Extremely Sparse Networks

no code implementations1 Jan 2021 Daejin Kim, Hyunjung Shim, Jongwuk Lee

We demonstrate that AAP equipped with existing pruning methods (i. e., iterative pruning, one-shot pruning, and dynamic pruning) consistently improves the accuracy of original methods at 128× - 4096× compression ratios on three benchmark datasets.

Network Pruning

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

Rethinking the Truly Unsupervised Image-to-Image Translation

1 code implementation ICCV 2021 Kyungjune Baek, Yunjey Choi, Youngjung Uh, Jaejun Yoo, Hyunjung Shim

To this end, we propose a truly unsupervised image-to-image translation model (TUNIT) that simultaneously learns to separate image domains and translates input images into the estimated domains.

Translation Unsupervised Image-To-Image Translation

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 +2

Collaborative Distillation for Top-N Recommendation

no code implementations13 Nov 2019 Jae-woong Lee, Minjin Choi, Jongwuk Lee, Hyunjung Shim

Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model.

Collaborative Filtering Knowledge Distillation

Attention-based Dropout Layer for Weakly Supervised Object Localization

1 code implementation CVPR 2019 Junsuk Choe, Hyunjung Shim

Weakly Supervised Object Localization (WSOL) techniques learn the object location only using image-level labels, without location annotations.

Object Weakly-Supervised Object Localization

Depth Reconstruction of Translucent Objects from a Single Time-of-Flight Camera using Deep Residual Networks

no code implementations28 Sep 2018 Seongjong Song, Hyunjung Shim

We propose a novel approach to recovering the translucent objects from a single time-of-flight (ToF) depth camera using deep residual networks.

Recycling the discriminator for improving the inference mapping of GAN

no code implementations27 Sep 2018 Duhyeon Bang, Hyunjung Shim

In order to analyze the real data in the latent space of GANs, it is necessary to investigate the inverse generation mapping from the data to the latent vector.

Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously

no code implementations20 Jul 2018 Kyungjune Baek, Duhyeon Bang, Hyunjung Shim

Also, we show that our model can achieve the competitive performance with the state-of-the-art attribute editing technique in terms of attribute editing quality.

Attribute Face Generation

Resembled Generative Adversarial Networks: Two Domains with Similar Attributes

no code implementations3 Jul 2018 Duhyeon Bang, Hyunjung Shim

We propose a novel algorithm, namely Resembled Generative Adversarial Networks (GAN), that generates two different domain data simultaneously where they resemble each other.

Vocal Bursts Valence Prediction

Generative Adversarial Networks for Unsupervised Object Co-localization

no code implementations1 Jun 2018 Junsuk Choe, Joo Hyun Park, Hyunjung Shim

Our important finding is that high image diversity of GAN, which is a main goal in GAN research, is ironically disadvantageous for object localization, because such discriminators focus not only on the target object, but also on the various objects, such as background objects.

Diversity Object +1

Discriminator Feature-based Inference by Recycling the Discriminator of GANs

no code implementations28 May 2018 Duhyeon Bang, Seoungyoon Kang, Hyunjung Shim

Various studies assert that the latent space of a GAN is semanticallymeaningful and can be utilized for advanced data analysis and manipulation.

MGGAN: Solving Mode Collapse using Manifold Guided Training

1 code implementation12 Apr 2018 Duhyeon Bang, Hyunjung Shim

Mode collapse is a critical problem in training generative adversarial networks.

Generative Adversarial Network

Improved Training of Generative Adversarial Networks Using Representative Features

no code implementations ICML 2018 Duhyeon Bang, Hyunjung Shim

Because the AE learns to minimize forward KL divergence, our GAN training with representative features is influenced by both reverse and forward KL divergence.

Diversity Image Generation

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