no code implementations • 18 Mar 2025 • Jaewoo Song, Daemin Park, Kanghyun Baek, Sangyub Lee, Jooyoung Choi, Eunji Kim, Sungroh Yoon
Developing effective visual inspection models remains challenging due to the scarcity of defect data.
no code implementations • 27 Feb 2025 • Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Sungroh Yoon
We propose EdiText, a controllable text editing method that modify the reference text to desired attributes at various scales.
no code implementations • 20 Jan 2025 • Jinwoong Chae, Sungwook Hong, SungKyu Kim, Sungroh Yoon, Gunn Kim
Transmission electron microscope (TEM) images are often corrupted by noise, hindering their interpretation.
no code implementations • 19 Jan 2025 • Junsung Park, Jungbeom Lee, Jongyoon Song, Sangwon Yu, Dahuin Jung, Sungroh Yoon
While CLIP has significantly advanced multimodal understanding by bridging vision and language, the inability to grasp negation - such as failing to differentiate concepts like "parking" from "no parking" - poses substantial challenges.
1 code implementation • 9 Jan 2025 • HyunGi Kim, Siwon Kim, Jisoo Mok, Sungroh Yoon
Deep Neural Networks have spearheaded remarkable advancements in time series forecasting (TSF), one of the major tasks in time series modeling.
no code implementations • 20 Dec 2024 • Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon
Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks.
no code implementations • 19 Dec 2024 • Yongsung Kim, MinJun Park, Jooyoung Choi, Sungroh Yoon
Recent learning-based Multi-View Stereo models have demonstrated state-of-the-art performance in sparse-view 3D reconstruction.
1 code implementation • 6 Dec 2024 • Jaihyun Lew, Soohyuk Jang, Jaehoon Lee, Seungryong Yoo, Eunji Kim, Saehyung Lee, Jisoo Mok, Siwon Kim, Sungroh Yoon
Transformers, a groundbreaking architecture proposed for Natural Language Processing (NLP), have also achieved remarkable success in Computer Vision.
no code implementations • 23 Nov 2024 • Chaehun Shin, Jooyoung Choi, Heeseung Kim, Sungroh Yoon
In this paper, we introduce Diptych Prompting, a novel zero-shot approach that reinterprets as an inpainting task with precise subject alignment by leveraging the emergent property of diptych generation in large-scale text-to-image models.
no code implementations • 22 Nov 2024 • Jooyoung Choi, Chaehun Shin, Yeongtak Oh, Heeseung Kim, Sungroh Yoon
Recent large-scale diffusion models generate high-quality images but struggle to learn new, personalized artistic styles, which limits the creation of unique style templates.
1 code implementation • 20 Nov 2024 • Sanghyeob Song, Jaihyun Lew, Hyemi Jang, Sungroh Yoon
To address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs.
1 code implementation • 31 Oct 2024 • Eunji Kim, Sriya Mantena, Weiwei Yang, Chandan Singh, Sungroh Yoon, Jianfeng Gao
It again provides a significant improvement over interpretable models (20% relative increase in the correlation of predicted fMRI responses), potentially enabling deeper scientific investigation of language selectivity in the brain.
1 code implementation • 28 Oct 2024 • Bong Gyun Kang, Dongjun Lee, HyunGi Kim, DoHyun Chung, Sungroh Yoon
To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure.
no code implementations • 24 Oct 2024 • Jongseon Kim, Hyungjoon Kim, HyunGi Kim, Dongjun Lee, Sungroh Yoon
By comparing and re-examining various deep learning models, we uncover new perspectives and presents the latest trends in time series forecasting, including the emergence of hybrid models, diffusion models, Mamba models, and foundation models.
no code implementations • 11 Oct 2024 • Eunji Kim, Kyuhong Shim, Simyung Chang, Sungroh Yoon
A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language.
no code implementations • 9 Oct 2024 • Sangwon Yu, Ik-hwan Kim, Jongyoon Song, Saehyung Lee, Junsung Park, Sungroh Yoon
LLMs often struggle to filter out irrelevant documents within the context, and their performance is sensitive to the position of supporting documents within that context.
1 code implementation • 30 Sep 2024 • Saehyung Lee, Jisoo Mok, Sangha Park, Yongho Shin, Dahuin Jung, Sungroh Yoon
Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models.
no code implementations • 22 Aug 2024 • Eunji Kim, Siwon Kim, MinJun Park, Rahim Entezari, Sungroh Yoon
Through analysis and experiments on various versions of SD, we demonstrate that our proposed approach effectively reduces bias without additional training, achieving both efficiency and preservation of core image generation functionality.
1 code implementation • 6 Aug 2024 • Jihun Yi, Sungroh Yoon
Although the identified Anomaly Cluster issue presents a significant challenge to applying k-nearest neighbor in UVAD, our proposed cleansing scheme effectively addresses this problem.
1 code implementation • 31 Jul 2024 • Sangwon Yu, Jongyoon Song, Bongkyu Hwang, Hoyoung Kang, Sooah Cho, Junhwa Choi, Seongho Joe, TaeHee Lee, Youngjune L. Gwon, Sungroh Yoon
Based on our observations and the rationale about attention-based model dynamics, we propose a negative attention score (NAS) to systematically and quantitatively formulate negative bias.
no code implementations • 29 Jul 2024 • Jihun Yi, Dahuin Jung, Sungroh Yoon
To address this challenge, we propose a method called Normality Addition via Normality Detection (NAND), leveraging a vision-language model.
1 code implementation • 25 Jun 2024 • Jaihyun Lew, Jooyoung Choi, Chaehun Shin, Dahuin Jung, Sungroh Yoon
In this paper, we introduce disentangled Motion Modeling (MoMo), a diffusion-based approach for VFI that enhances visual quality by focusing on intermediate motion modeling.
no code implementations • 20 Jun 2024 • Jongyoon Song, Sangwon Yu, Sungroh Yoon
In this paper, we identify a new category of bias that induces input-conflicting hallucinations, where large language models (LLMs) generate responses inconsistent with the content of the input context.
no code implementations • 18 Jun 2024 • Kukjin Choi, Jihun Yi, Jisoo Mok, Sungroh Yoon
Continuous efforts are being made to advance anomaly detection in various manufacturing processes to increase the productivity and safety of industrial sites.
1 code implementation • 5 Jun 2024 • Saehyung Lee, Sangwon Yu, Junsung Park, Jihun Yi, Sungroh Yoon
In this paper, we primarily address the issue of dialogue-form context query within the interactive text-to-image retrieval task.
1 code implementation • 16 Mar 2024 • Uiwon Hwang, Jonghyun Lee, Juhyeon Shin, Sungroh Yoon
We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space.
Ranked #1 on
Domain Adaptation
on DomainNet
1 code implementation • 16 Mar 2024 • Yeongtak Oh, Jonghyun Lee, Jooyoung Choi, Dahuin Jung, Uiwon Hwang, Sungroh Yoon
To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme.
1 code implementation • 12 Mar 2024 • Jonghyun Lee, Dahuin Jung, Saehyung Lee, Junsung Park, Juhyeon Shin, Uiwon Hwang, Sungroh Yoon
To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error.
Ranked #1 on
Test-time Adaptation
on ImageNet-C
1 code implementation • 8 Mar 2024 • Daegyu Kim, Jooyoung Choi, Chaehun Shin, Uiwon Hwang, Sungroh Yoon
Our approach aims to approximate and integrate optimal transport into the training process, significantly enhancing the ability of diffusion models to estimate the denoiser outputs accurately.
no code implementations • 23 Feb 2024 • Jongyoon Song, Nohil Park, Bongkyu Hwang, Jaewoong Yun, Seongho Joe, Youngjune L. Gwon, Sungroh Yoon
Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input document.
no code implementations • 14 Feb 2024 • Siwon Kim, Shuyang Dai, Mohammad Kachuee, Shayan Ray, Tara Taghavi, Sungroh Yoon
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content.
no code implementations • 14 Feb 2024 • Juhyeon Shin, Jonghyun Lee, Saehyung Lee, MinJun Park, Dongjun Lee, Uiwon Hwang, Sungroh Yoon
In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label.
1 code implementation • 8 Feb 2024 • Heeseung Kim, Soonshin Seo, Kyeongseok Jeong, Ohsung Kwon, Soyoon Kim, Jungwhan Kim, Jaehong Lee, Eunwoo Song, Myungwoo Oh, Jung-Woo Ha, Sungroh Yoon, Kang Min Yoo
To construct USDM, we fine-tune our speech-text model on spoken dialog data using a multi-step spoken dialog template that stimulates the chain-of-reasoning capabilities exhibited by the underlying LLM.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
1 code implementation • 23 Jan 2024 • Hyungyu Lee, Saehyung Lee, Hyemi Jang, Junsung Park, Ho Bae, Sungroh Yoon
The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem.
1 code implementation • 19 Jan 2024 • Yeongtak Oh, Saehyung Lee, Uiwon Hwang, Sungroh Yoon
Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models.
no code implementations • 2 Dec 2023 • Yeongtak Oh, Jooyoung Choi, Yongsung Kim, MinJun Park, Chaehun Shin, Sungroh Yoon
Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation.
no code implementations • 14 Nov 2023 • Nohil Park, Joonsuk Park, Kang Min Yoo, Sungroh Yoon
An exciting advancement in the field of multilingual models is the emergence of autoregressive models with zero- and few-shot capabilities, a phenomenon widely reported in large-scale language models.
1 code implementation • 13 Nov 2023 • Sangwon Yu, Changmin Lee, Hojin Lee, Sungroh Yoon
To facilitate this process, ScoPE employs a training objective that maximizes a target score, thoroughly considering both the ability to guide the text and its fluency.
1 code implementation • NeurIPS 2023 • Hyemi Jang, Junsung Park, Dahuin Jung, Jaihyun Lew, Ho Bae, Sungroh Yoon
Blind-spot networks (BSNs) have been a prevalent choice to ensure J-invariance in self-supervised image denoising.
1 code implementation • NeurIPS 2023 • Sungwon Kim ~Sungwon_Kim2, Kevin J. Shih, Rohan Badlani, Joao Felipe Santos, Evelina Bakhturina, Mikyas T. Desta, Rafael Valle, Sungroh Yoon, Bryan Catanzaro
P-Flow comprises a speech-prompted text encoder for speaker adaptation and a flow matching generative decoder for high-quality and fast speech synthesis.
no code implementations • 25 Aug 2023 • Yang Jeong Park, Sung Eun Jerng, Jin-Sung Park, Choah Kwon, Chia-Wei Hsu, Zhichu Ren, Sungroh Yoon, Ju Li
The advent of artificial intelligence (AI) has enabled a comprehensive exploration of materials for various applications.
no code implementations • 28 Jun 2023 • Jiwon Park, Jeonghee Jo, Sungroh Yoon
Mass spectra, which are agglomerations of ionized fragments from targeted molecules, play a crucial role across various fields for the identification of molecular structures.
1 code implementation • 8 Jun 2023 • Seungryong Yoo, Eunji Kim, Dahuin Jung, Jungbeom Lee, Sungroh Yoon
Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks.
Ranked #2 on
Visual Prompt Tuning
on VTAB-1k(Natural<7>)
2 code implementations • 2 Jun 2023 • Eunji Kim, Dahuin Jung, Sangha Park, Siwon Kim, Sungroh Yoon
To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM).
no code implementations • 30 May 2023 • Daegyu Kim, Chaehun Shin, Jooyoung Choi, Dahuin Jung, Sungroh Yoon
Diffusion-Stego achieved a high capacity of messages (3. 0 bpp of binary messages with 98% accuracy, and 6. 0 bpp with 90% accuracy) as well as high quality (with a FID score of 2. 77 for 1. 0 bpp on the FFHQ 64$\times$64 dataset) that makes it challenging to distinguish from real images in the PNG format.
no code implementations • 25 May 2023 • Jooyoung Choi, Yunjey Choi, Yunji Kim, Junho Kim, Sungroh Yoon
Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts.
no code implementations • 25 May 2023 • Hyeongrok Han, Siwon Kim, Hyun-Soo Choi, Sungroh Yoon
Several recent studies have elucidated why knowledge distillation (KD) improves model performance.
no code implementations • 14 Mar 2023 • Dahuin Jung, Hyungyu Lee, Sungroh Yoon
In particular, in comparison with existing self-supervised learning methods for tabular data, we propose a different corruption method for state and action representations that is robust to diverse distortions.
no code implementations • 14 Mar 2023 • Chaehun Shin, Heeseung Kim, Che Hyun Lee, Sang-gil Lee, Sungroh Yoon
Despite the fact that text-to-video (TTV) model has recently achieved remarkable success, there have been few approaches on TTV for its extension to video editing.
1 code implementation • 17 Feb 2023 • Dahuin Jung, Dongjin Lee, Sunwon Hong, Hyemi Jang, Ho Bae, Sungroh Yoon
The aim of continual learning is to learn new tasks continuously (i. e., plasticity) without forgetting previously learned knowledge from old tasks (i. e., stability).
1 code implementation • 25 Oct 2022 • Jaehee Jang, Heonseok Ha, Dahuin Jung, Sungroh Yoon
While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient.
no code implementations • CVPR 2022 • Jongwan Kim, Dongjin Lee, Byunggook Na, Seongsik Park, Jeonghee Jo, Sungroh Yoon
In terms of image quality, the LPIPS score improves by up to 12% and the reconstruction speed is 87% higher than that of ET-Net.
1 code implementation • 14 Jun 2022 • Jonghyun Lee, Dahuin Jung, Junho Yim, Sungroh Yoon
Unlike existing confidence scores that use only one of the source or target domain knowledge, the JMDS score uses both knowledge.
no code implementations • 10 Jun 2022 • Geonho Cha, Chaehun Shin, Sungroh Yoon, Dongyoon Wee
Finally, for each element in the feature set, the aggregation features are extracted by calculating the weighted means and variances, where the weights are derived from the similarity distributions.
5 code implementations • 9 Jun 2022 • Sang-gil Lee, Wei Ping, Boris Ginsburg, Bryan Catanzaro, Sungroh Yoon
Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments.
Ranked #2 on
Speech Synthesis
on LibriTTS
(using extra training data)
no code implementations • 30 May 2022 • Sungwon Kim, Heeseung Kim, Sungroh Yoon
We train the speaker-conditional diffusion model on large-scale untranscribed datasets for a classifier-free guidance method and further fine-tune the diffusion model on the reference speech of the target speaker for adaptation, which only takes 40 seconds.
no code implementations • 11 Apr 2022 • Jungbeom Lee, Eunji Kim, Jisoo Mok, Sungroh Yoon
This manipulation is realized in an anti-adversarial manner, so that the original image is perturbed along pixel gradients in directions opposite to those used in an adversarial attack.
5 code implementations • CVPR 2022 • Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon
Diffusion models learn to restore noisy data, which is corrupted with different levels of noise, by optimizing the weighted sum of the corresponding loss terms, i. e., denoising score matching loss.
no code implementations • CVPR 2022 • Eunji Kim, Siwon Kim, Jungbeom Lee, Hyunwoo Kim, Sungroh Yoon
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels.
1 code implementation • CVPR 2022 • Jisoo Mok, Byunggook Na, Ji-Hoon Kim, Dongyoon Han, Sungroh Yoon
To take such non-linear characteristics into account, we introduce Label-Gradient Alignment (LGA), a novel NTK-based metric whose inherent formulation allows it to capture the large amount of non-linear advantage present in modern neural architectures.
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
2 code implementations • 7 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.
1 code implementation • 30 Jan 2022 • Byunggook Na, Jisoo Mok, Seongsik Park, Dongjin Lee, Hyeokjun Choe, Sungroh Yoon
We investigate the design choices used in the previous studies in terms of the accuracy and number of spikes and figure out that they are not best-suited for SNNs.
no code implementations • CVPR 2022 • Jaihyun Koh, Jangho Lee, Sungroh Yoon
The images captured by under-display cameras (UDCs) are degraded by the screen in front of them.
2 code implementations • 2 Dec 2021 • Sang-gil Lee, Eunji Kim, Jae Seok Bae, Jung Hoon Kim, Sungroh Yoon
The computer-aided diagnosis of focal liver lesions (FLLs) can help improve workflow and enable correct diagnoses; FLL detection is the first step in such a computer-aided diagnosis.
Automatic Liver And Tumor Segmentation
Computed Tomography (CT)
+4
no code implementations • 24 Nov 2021 • Sungmin Cha, Seonwoo Min, Sungroh Yoon, Taesup Moon
Namely, we make the supervised pre-training of Neural DUDE compatible with the adaptive fine-tuning of the parameters based on the given noisy data subject to denoising.
no code implementations • 23 Nov 2021 • Heeseung Kim, Sungwon Kim, Sungroh Yoon
For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset.
no code implementations • 23 Oct 2021 • Byunggook Na, Jaehee Jang, Seongsik Park, Seijoon Kim, Joonoo Kim, Moon Sik Jeong, Kwang Choon Kim, Seon Heo, Yoonsang Kim, Sungroh Yoon
We implemented large-batch synchronous training of DNNs based on Caffe, a deep learning library.
1 code implementation • NeurIPS 2021 • Jungbeom Lee, Jooyoung Choi, Jisoo Mok, Sungroh Yoon
Weakly supervised semantic segmentation produces pixel-level localization from class labels; however, a classifier trained on such labels is likely to focus on a small discriminative region of the target object.
Ranked #20 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
no code implementations • 2 Oct 2021 • Yonghyun Jeong, Jooyoung Choi, Sungwon Kim, Youngmin Ro, Tae-Hyun Oh, Doyeon Kim, Heonseok Ha, Sungroh Yoon
In this work, we present Facial Identity Controllable GAN (FICGAN) for not only generating high-quality de-identified face images with ensured privacy protection, but also detailed controllability on attribute preservation for enhanced data utility.
no code implementations • 29 Sep 2021 • Heeseung Kim, Sungwon Kim, Sungroh Yoon
By modeling the unconditional distribution for speech, our model can utilize the untranscribed data for training.
no code implementations • 29 Sep 2021 • Jonghyun Lee, Dahuin Jung, Junho Yim, Sungroh Yoon
Unsupervised domain adaptation (UDA) aims to achieve high performance within the unlabeled target domain by leveraging the labeled source domain.
no code implementations • 29 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.
no code implementations • 29 Sep 2021 • Jae Myung Kim, Eunji Kim, Sungroh Yoon, Jungwoo Lee, Cordelia Schmid, Zeynep Akata
Explaining a complex black-box system in a post-hoc manner is important to understand its predictions.
no code implementations • EMNLP 2021 • Jongyoon Song, Sungwon Kim, Sungroh Yoon
Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition.
1 code implementation • 11 Sep 2021 • Siwon Kim, Kukjin Choi, Hyun-Soo Choi, Byunghan Lee, Sungroh Yoon
Furthermore, we question the potential of existing TAD methods by showing that an untrained model obtains comparable detection performance to the existing methods even when PA is forbidden.
no code implementations • ACL 2022 • Sangwon Yu, Jongyoon Song, Heeseung Kim, Seong-min Lee, Woo-Jong Ryu, Sungroh Yoon
AGG addresses the degeneration problem by gating the specific part of the gradient for rare token embeddings.
1 code implementation • ICCV 2021 • Jooyoung Choi, Sungwon Kim, Yonghyun Jeong, Youngjune Gwon, Sungroh Yoon
In this work, we propose Iterative Latent Variable Refinement (ILVR), a method to guide the generative process in DDPM to generate high-quality images based on a given reference image.
2 code implementations • ICCV 2021 • Jooyoung Choi, Jungbeom Lee, Yonghyun Jeong, Sungroh Yoon
From our observations, the generator's implicit positional encoding is translation-variant, making the generator spatially biased.
1 code implementation • ICCV 2021 • Jisoo Mok, Byunggook Na, Hyeokjun Choe, Sungroh Yoon
Current efforts to improve the robustness of neural networks against adversarial examples are focused on developing robust training methods, which update the weights of a neural network in a more robust direction.
1 code implementation • 23 Jul 2021 • Seonwoo Min, Byunghan Lee, Sungroh Yoon
Results: In this paper, we introduce TargetNet, a novel deep learning-based algorithm for functional miRNA target prediction.
1 code implementation • 29 Jun 2021 • Bumju Kwak, Jiwon Park, Taewon Kang, Jeonghee Jo, Byunghan Lee, Sungroh Yoon
In recent years, molecular representation learning has emerged as a key area of focus in various chemical tasks.
no code implementations • 14 Jun 2021 • Dongjin Lee, Seongsik Park, Jongwan Kim, Wuhyeong Doh, Sungroh Yoon
On MNIST dataset, our proposed student SNN achieves up to 0. 09% higher accuracy and produces 65% less spikes compared to the student SNN trained with conventional knowledge distillation method.
no code implementations • 14 Jun 2021 • Jeonghee Jo, Bumju Kwak, Byunghan Lee, Sungroh Yoon
Message passing neural network provides an effective framework for capturing molecular geometric features with the perspective of a molecule as a graph.
1 code implementation • ICLR 2022 • Sang-gil Lee, Heeseung Kim, Chaehun Shin, Xu Tan, Chang Liu, Qi Meng, Tao Qin, Wei Chen, Sungroh Yoon, Tie-Yan Liu
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density.
1 code implementation • 9 Jun 2021 • Byunggook Na, Jisoo Mok, Hyeokjun Choe, Sungroh Yoon
By analyzing proxy data constructed using various selection methods through data entropy, we propose a novel proxy data selection method tailored for NAS.
1 code implementation • ICLR 2022 • Uiwon Hwang, Heeseung Kim, Dahuin Jung, Hyemi Jang, Hyungyu Lee, Sungroh Yoon
Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner.
no code implementations • 4 Jun 2021 • Seongsik Park, Sungroh Yoon
With TTFS coding, each neuron generates one spike at most, which leads to a significant improvement in energy efficiency.
no code implementations • 22 Apr 2021 • Seongsik Park, Dongjin Lee, Sungroh Yoon
Spiking neural networks (SNNs) have emerged as energy-efficient neural networks with temporal information.
1 code implementation • CVPR 2021 • Eunji Kim, Siwon Kim, Minji Seo, Sungroh Yoon
Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases.
1 code implementation • CVPR 2021 • Jungbeom Lee, Eunji Kim, Sungroh Yoon
Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object.
1 code implementation • CVPR 2021 • Jungbeom Lee, Jihun Yi, Chaehun Shin, Sungroh Yoon
Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object.
1 code implementation • ICLR 2021 • Saehyung Lee, Changhwa Park, Hyungyu Lee, Jihun Yi, Jonghyun Lee, Sungroh Yoon
Herein, we propose a data augmentation method to improve generalization in both adversarial and standard learning by using out-of-distribution (OOD) data that are devoid of the abovementioned issues.
no code implementations • 1 Jan 2021 • Jae Myung Kim, Eunji Kim, Seokhyeon Ha, Sungroh Yoon, Jungwoo Lee
Saliency maps have been widely used to explain the behavior of an image classifier.
no code implementations • EMNLP 2020 • Siwon Kim, Jihun Yi, Eunji Kim, Sungroh Yoon
To demystify the "black box" property of deep neural networks for natural language processing (NLP), several methods have been proposed to interpret their predictions by measuring the change in prediction probability after erasing each token of an input.
1 code implementation • 23 Sep 2020 • Jihun Yi, Eunji Kim, Siwon Kim, Sungroh Yoon
IG map provides a class-independent answer to "How informative is each pixel?
no code implementations • ECCV 2020 • Dahuin Jung, Jonghyun Lee, Jihun Yi, Sungroh Yoon
We propose an interpretable Capsule Network, iCaps, for image classification.
3 code implementations • 29 Jun 2020 • Jihun Yi, Sungroh Yoon
In this paper, we address the problem of image anomaly detection and segmentation.
Ranked #12 on
Anomaly Detection
on BTAD
(Segmentation AUROC metric, using extra
training data)
1 code implementation • 18 Jun 2020 • Changhwa Park, Jonghyun Lee, Jaeyoon Yoo, Minhoe Hur, Sungroh Yoon
Enhancing feature transferability by matching marginal distributions has led to improvements in domain adaptation, although this is at the expense of feature discrimination.
1 code implementation • NeurIPS 2020 • Sang-gil Lee, Sungwon Kim, Sungroh Yoon
Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis.
6 code implementations • NeurIPS 2020 • Jaehyeon Kim, Sungwon Kim, Jungil Kong, Sungroh Yoon
By leveraging the properties of flows, MAS searches for the most probable monotonic alignment between text and the latent representation of speech.
Ranked #4 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
no code implementations • 26 Mar 2020 • Seongsik Park, Seijoon Kim, Byunggook Na, Sungroh Yoon
Spiking neural networks (SNNs) have gained considerable interest due to their energy-efficient characteristics, yet lack of a scalable training algorithm has restricted their applicability in practical machine learning problems.
2 code implementations • CVPR 2020 • Saehyung Lee, Hyungyu Lee, Sungroh Yoon
In this paper, we identify Adversarial Feature Overfitting (AFO), which may cause poor adversarially robust generalization, and we show that adversarial training can overshoot the optimal point in terms of robust generalization, leading to AFO in our simple Gaussian model.
1 code implementation • 25 Nov 2019 • Seonwoo Min, Seunghyun Park, Siwon Kim, Hyun-Soo Choi, Byunghan Lee, Sungroh Yoon
Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling.
Ranked #17 on
Only Connect Walls Dataset Task 1 (Grouping)
on OCW
(using extra training data)
no code implementations • ICCV 2019 • Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon
We propose a method of using videos automatically harvested from the web to identify a larger region of the target object by using temporal information, which is not present in the static image.
no code implementations • 26 Apr 2019 • Dongjun Lee, Jaesik Yoon, Jongyun Song, Sang-gil Lee, Sungroh Yoon
We show that our model outperforms state-of-the-art approaches for various text-to-SQL datasets in two aspects: 1) the SQL generation accuracy for the trained templates, and 2) the adaptability to the unseen SQL templates based on a single example without any additional training.
no code implementations • 12 Mar 2019 • Jaeyoon Yoo, Changhwa Park, Yongjun Hong, Sungroh Yoon
We propose a novel domain adaptation method based on label propagation and cycle consistency to let the clusters of the features from the two domains overlap exactly and become clear for high accuracy.
no code implementations • 12 Mar 2019 • Seijoon Kim, Seongsik Park, Byunggook Na, Sungroh Yoon
Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications.
no code implementations • 2 Mar 2019 • Uiwon Hwang, Jaewoo Park, Hyemi Jang, Sungroh Yoon, Nam Ik Cho
Deep neural networks are widely used and exhibit excellent performance in many areas.
Ranked #2 on
Adversarial Defense against FGSM Attack
on MNIST
no code implementations • 28 Feb 2019 • Dahuin Jung, Ho Bae, Hyun-Soo Choi, Sungroh Yoon
We propose a DL based steganalysis technique that effectively removes secret images by restoring the distribution of the original images.
no code implementations • CVPR 2019 • Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon
The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations.
1 code implementation • 26 Feb 2019 • Uiwon Hwang, Dahuin Jung, Sungroh Yoon
We evaluate the classification performance (F1-score) of the proposed method with 20% missingness and confirm up to a 5% improvement in comparison with the performance of combinations of state-of-the-art methods.
no code implementations • 31 Jan 2019 • Ho Bae, Dahuin Jung, Sungroh Yoon
We compared our method to state-of-the-art techniques and observed that our method preserves the same level of privacy as differential privacy (DP), but had better prediction results.
no code implementations • 30 Jan 2019 • Dahuin Jung, Ho Bae, Hyun-Soo Choi, Sungroh Yoon
The cover image with the secret message is called a stego image.
2 code implementations • 6 Nov 2018 • Sungwon Kim, Sang-gil Lee, Jongyoon Song, Sungroh Yoon
Most of modern text-to-speech architectures use a WaveNet vocoder for synthesizing a high-fidelity waveform audio, but there has been a limitation for practical applications due to its slow autoregressive sampling scheme.
Sound Audio and Speech Processing
no code implementations • 10 Sep 2018 • Seongsik Park, Seijoon Kim, Hyeokjun Choe, Sungroh Yoon
The spiking neural networks (SNNs) are considered as one of the most promising artificial neural networks due to their energy efficient computing capability.
no code implementations • 31 Jul 2018 • Ho Bae, Jaehee Jang, Dahuin Jung, Hyemi Jang, Heonseok Ha, Hyungyu Lee, Sungroh Yoon
Furthermore, the privacy of the data involved in model training is also threatened by attacks such as the model-inversion attack, or by dishonest service providers of AI applications.
1 code implementation • 2 Jul 2018 • Sang-gil Lee, Jae Seok Bae, Hyunjae Kim, Jung Hoon Kim, Sungroh Yoon
We present a focal liver lesion detection model leveraged by custom-designed multi-phase computed tomography (CT) volumes, which reflects real-world clinical lesion detection practice using a Single Shot MultiBox Detector (SSD).
no code implementations • 29 May 2018 • Sungmin Lee, Jangho Lee, Jungbeom Lee, Chul-Kee Park, Sungroh Yoon
There have been various studies concerning automated lesion detection.
no code implementations • 28 May 2018 • Heonseok Ha, Uiwon Hwang, Yongjun Hong, Jahee Jang, Sungroh Yoon
Knowledge tracing (KT), a key component of an intelligent tutoring system, is a machine learning technique that estimates the mastery level of a student based on his/her past performance.
no code implementations • 21 May 2018 • Seongsik Park, Jaehee Jang, Seijoon Kim, Sungroh Yoon
Memory-augmented neural networks (MANNs) are designed for question-answering tasks.
no code implementations • 16 Apr 2018 • Jaekoo Lee, Byunghan Lee, Jongyoon Song, Jaesik Yoon, Yongsik Lee, Dong-hun Lee, Sungroh Yoon
The experimental results with real-world data confirm the effectiveness of the system and models.
no code implementations • 13 Apr 2018 • Jungbeom Lee, Jangho Lee, Sungmin Lee, Sungroh Yoon
Video prediction can be performed by finding features in recent frames, and using them to generate approximations to upcoming frames.
Ranked #1 on
Video Prediction
on KTH
(Cond metric)
no code implementations • 17 Jan 2018 • Sungwoon Choi, Heonseok Ha, Uiwon Hwang, Chanju Kim, Jung-Woo Ha, Sungroh Yoon
A recommender system aims to recommend items that a user is interested in among many items.
no code implementations • 11 Dec 2017 • Jaeyoon Yoo, Yongjun Hong, Yung-Kyun Noh, Sungroh Yoon
The objective of this study is to train an autonomous navigation model that uses a simulator (instead of real labeled data) and an inexpensive monocular camera.
1 code implementation • NeurIPS 2017 • Seunghyun Park, Seonwoo Min, Hyun-Soo Choi, Sungroh Yoon
MicroRNAs (miRNAs) are small non-coding ribonucleic acids (RNAs) which play key roles in post-transcriptional gene regulation.
no code implementations • 28 Nov 2017 • Jaehee Jang, Byungook Na, Sungroh Yoon
Distributed training of deep neural networks has received significant research interest, and its major approaches include implementations on multiple GPUs and clusters.
no code implementations • 16 Nov 2017 • Yongjun Hong, Uiwon Hwang, Jaeyoon Yoo, Sungroh Yoon
Generative Adversarial Networks (GAN) have received wide attention in the machine learning field for their potential to learn high-dimensional, complex real data distribution.
no code implementations • 11 Nov 2017 • Uiwon Hwang, Sungwoon Choi, Han-Byoel Lee, Sungroh Yoon
Electronic health records (EHRs) have contributed to the computerization of patient records and can thus be used not only for efficient and systematic medical services, but also for research on biomedical data science.
no code implementations • 10 Nov 2017 • Seongsik Park, Seijoon Kim, Seil Lee, Ho Bae, Sungroh Yoon
In this paper, we identify memory addressing (specifically, content-based addressing) as the main reason for the performance degradation and propose a robust quantization method for MANNs to address the challenge.
1 code implementation • 31 Oct 2017 • Sang-gil Lee, Uiwon Hwang, Seonwoo Min, Sungroh Yoon
We propose an application of sequence generative adversarial networks (SeqGAN), which are generative adversarial networks for discrete sequence generation, for creating polyphonic musical sequences.
Sound Audio and Speech Processing
no code implementations • 28 Jun 2017 • Jaeyoon Yoo, Heonseok Ha, Jihun Yi, Jongha Ryu, Chanju Kim, Jung-Woo Ha, Young-Han Kim, Sungroh Yoon
Recommender systems aim to find an accurate and efficient mapping from historic data of user-preferred items to a new item that is to be liked by a user.
2 code implementations • 27 Apr 2017 • Sunyoung Kwon, Sungroh Yoon
To guarantee the commutative property for homogeneous interaction, we apply model sharing and hidden representation merging techniques.
no code implementations • 27 Apr 2017 • Ho Bae, Byunghan Lee, Sunyoung Kwon, Sungroh Yoon
We compare our proposed method to various existing methods and biological sequence analysis methods implemented on top of our framework.
no code implementations • 2 Apr 2017 • Jae-hong Park, Jongyoon Song, Sungroh Yoon
Experiments on Czech-German and French-German translations demonstrate the efficacy of the proposed pseudo parallel corpus, which shows not only enhanced results for bidirectional translation tasks but also substantial improvement with the aid of a ground truth real parallel corpus.
no code implementations • 15 Nov 2016 • Jaekoo Lee, Hyunjae Kim, Jongsun Lee, Sungroh Yoon
Graphs provide a powerful means for representing complex interactions between entities.
no code implementations • 12 Nov 2016 • Jangho Lee, Gyuwan Kim, Jaeyoon Yoo, Changwoo Jung, Minseok Kim, Sungroh Yoon
Under the assumption that using such an automatically generated dataset could relieve the burden of manual question-answer generation, we tried to use this dataset to train an instance of Watson and checked the training efficiency and accuracy.
no code implementations • 8 Nov 2016 • Seongsik Park, Sang-gil Lee, Hyunha Nam, Sungroh Yoon
In order to eliminate this workaround, recently proposed is a new class of SNN named deep spiking networks (DSNs), which can be trained directly (without a mapping from conventional deep networks) by error backpropagation with stochastic gradient descent.
no code implementations • 6 Nov 2016 • Gyuwan Kim, Hayoon Yi, Jangho Lee, Yunheung Paek, Sungroh Yoon
In computer security, designing a robust intrusion detection system is one of the most fundamental and important problems.
no code implementations • 6 Oct 2016 • Hyeokjun Choe, Seil Lee, Hyunha Nam, Seongsik Park, Seijoon Kim, Eui-Young Chung, Sungroh Yoon
The second is the popularity of NAND flash-based solid-state drives (SSDs) containing multicore processors that can accommodate extra computation for data processing.
no code implementations • NeurIPS 2016 • Taesup Moon, Seonwoo Min, Byunghan Lee, Sungroh Yoon
We present a new framework of applying deep neural networks (DNN) to devise a universal discrete denoiser.
no code implementations • 29 Apr 2016 • Seunghyun Park, Seonwoo Min, Hyun-Soo Choi, Sungroh Yoon
Since microRNAs (miRNAs) play a crucial role in post-transcriptional gene regulation, miRNA identification is one of the most essential problems in computational biology.
1 code implementation • 30 Mar 2016 • Byunghan Lee, Junghwan Baek, Seunghyun Park, Sungroh Yoon
MicroRNAs (miRNAs) are short sequences of ribonucleic acids that control the expression of target messenger RNAs (mRNAs) by binding them.
no code implementations • 21 Mar 2016 • Seonwoo Min, Byunghan Lee, Sungroh Yoon
In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics.
no code implementations • 26 Feb 2016 • Hanjoo Kim, Jae-hong Park, Jaehee Jang, Sungroh Yoon
The increasing complexity of deep neural networks (DNNs) has made it challenging to exploit existing large-scale data processing pipelines for handling massive data and parameters involved in DNN training.
no code implementations • 16 Dec 2015 • Byunghan Lee, Taehoon Lee, Byunggook Na, Sungroh Yoon
A eukaryotic gene consists of multiple exons (protein coding regions) and introns (non-coding regions), and a splice junction refers to the boundary between a pair of exon and intron.
no code implementations • 19 Nov 2015 • Taehoon Lee, Minsuk Choi, Sungroh Yoon
Learning meaningful representations using deep neural networks involves designing efficient training schemes and well-structured networks.
1 code implementation • 16 Nov 2015 • Sunyoung Kwon, Gyuwan Kim, Byunghan Lee, Jongsik Chun, Sungroh Yoon, Young-Han Kim
Motivated by the need for fast and accurate classification of unlabeled nucleotide sequences on a large scale, we developed NASCUP, a new classification method that captures statistical structures of nucleotide sequences by compact context-tree models and universal probability from information theory.
Genomics Information Theory Information Theory
no code implementations • 21 Feb 2015 • Taehoon Lee, Taesup Moon, Seung Jean Kim, Sungroh Yoon
Robust classification becomes challenging when each class consists of multiple subclasses.