46 citations · 208 across the 25 of their papers we have counts for
25 papers
Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion
Eunji Kim, Siwon Kim, Minjun Park +2
Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing de-biasing techniques rely heavily on additional training, whic…
ControlDreamer: Blending Geometry and Style in Text-to-3D
Yeongtak Oh, Jooyoung Choi, Yongsung Kim +3
Recent advancements in text-to-3D generation have significantly contributed to the automation and democratization of 3D content creation. Building upon these developments, we aim t…
On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
Sangha Park, Jisoo Mok, Dahuin Jung +2
Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection…
PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising
Hyemi Jang, Junsung Park, Dahuin Jung +3
Although supervised image denoising networks have shown remarkable performance on synthesized noisy images, they often fail in practice due to the difference between real and synth…
ProPILE: Probing Privacy Leakage in Large Language Models
Siwon Kim, Sangdoo Yun, Hwaran Lee +3
The rapid advancement and widespread use of large language models (LLMs) have raised significant concerns regarding the potential leakage of personally identifiable information (PI…
Improving Visual Prompt Tuning for Self-supervised Vision Transformers
Seungryong Yoo, Eunji Kim, Dahuin Jung +2
Visual Prompt Tuning (VPT) is an effective tuning method for adapting pretrained Vision Transformers (ViTs) to downstream tasks. It leverages extra learnable tokens, known as promp…
Probabilistic Concept Bottleneck Models
Eunji Kim, Dahuin Jung, Sangha Park +2
Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept predicti…
Diffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection
Daegyu Kim, Chaehun Shin, Jooyoung Choi +2
Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models t…
Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models
Jooyoung Choi, Yunjey Choi, Yunji Kim +2
Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided imag…
Edit-A-Video: Single Video Editing with Object-Aware Consistency
Chaehun Shin, Heeseung Kim, Che Hyun Lee +2
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. Motivated by app…
Sample-efficient Adversarial Imitation Learning
Dahuin Jung, Hyungyu Lee, Sungroh Yoon
Imitation learning, in which learning is performed by demonstration, has been studied and advanced for sequential decision-making tasks in which a reward function is not predefined…
Confidence Score for Source-Free Unsupervised Domain Adaptation
Jonghyun Lee, Dahuin Jung, Junho Yim +1
Source-free unsupervised domain adaptation (SFUDA) aims to obtain high performance in the unlabeled target domain using the pre-trained source model, not the source data. Existing…
Out of Sight, Out of Mind: A Source-View-Wise Feature Aggregation for Multi-View Image-Based Rendering
Geonho Cha, Chaehun Shin, Sungroh Yoon +1
To estimate the volume density and color of a 3D point in the multi-view image-based rendering, a common approach is to inspect the consensus existence among the given source image…
E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations
Jongwan Kim, DongJin Lee, Byunggook Na +3
Event cameras respond to brightness changes in the scene asynchronously and independently for every pixel. Due to the properties, these cameras have distinct features: high dynamic…
BigVGAN: A Universal Neural Vocoder with Large-Scale Training
Sang-gil Lee, Wei Ping, Boris Ginsburg +2
Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthe…
Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
Sungwon Kim, Heeseung Kim, Sungroh Yoon
We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with…
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Jungbeom Lee, Eunji Kim, Jisoo Mok +1
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a train…
Perception Prioritized Training of Diffusion Models
Jooyoung Choi, Jungbeom Lee, Chaehun Shin +3
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 sco…
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization
Eunji Kim, Siwon Kim, Jungbeom Lee +2
Weakly supervised object localization aims to find a target object region in a given image with only weak supervision, such as image-level labels. Most existing methods use a class…
Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
Jungbeom Lee, Seong Joon Oh, Sangdoo Yun +3
Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps obtained from a classifier. However, training on class labels only, classifi…
Dataset Condensation with Contrastive Signals
Saehyung Lee, Sanghyuk Chun, Sangwon Jung +2
Recent studies have demonstrated that gradient matching-based dataset synthesis, or dataset condensation (DC), methods can achieve state-of-the-art performance when applied to data…
Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation
Sung-Hoon Yoon, Hyeokjun Kweon, Jaeseok Jeong +3
Existing studies in weakly supervised semantic segmentation (WSSS) have utilized class activation maps (CAMs) to localize the class objects. However, since a classification loss is…
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation
Lin Wang, Yujeong Chae, Sung-Hoon Yoon +2
Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur, showing advantages over conventional cameras. A…
Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings
Sangwon Yu, Jongyoon Song, Heeseung Kim +3
Recent studies have determined that the learned token embeddings of large-scale neural language models are degenerated to be anisotropic with a narrow-cone shape. This phenomenon,…