14 papers
3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation
Seonho Lee, Jiho Choi, Inha Kang +3
Vision-Language Models (VLMs) have shown remarkable performance on diverse visual and linguistic tasks, yet they remain fundamentally limited in their understanding of 3D spatial s…
Rethinking Direct Preference Optimization in Diffusion Models
Junyong Kang, Seohyun Lim, Kyungjune Baek +1
Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optim…
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
Hyogon Ryu, NaHyeon Park, Hyunjung Shim
Despite the widespread use of text-to-image diffusion models across various tasks, their computational and memory demands limit practical applications. To mitigate this issue, quan…
Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation
Jiho Choi, Seonho Lee, Minhyun Lee +2
Open-Vocabulary Part Segmentation (OVPS) is an emerging field for recognizing fine-grained parts in unseen categories. We identify two primary challenges in OVPS: (1) the difficult…
MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval
Seojeong Park, Jiho Choi, Kyungjune Baek +1
Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retri…
MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
Minhyun Lee, Seungho Lee, Song Park +3
Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions.…
Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation
Seungho Lee, Hwijeong Lee, Hyunjung Shim
We address the challenges of the semi-supervised LiDAR segmentation (SSLS) problem, particularly in low-budget scenarios. The two main issues in low-budget SSLS are the poor-qualit…
Scribble-Guided Diffusion for Training-free Text-to-Image Generation
Seonho Lee, Jiho Choi, Seohyun Lim +2
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using te…
DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation
Jiwook Kim, Seonho Lee, Jaeyo Shin +2
Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing. However, existing SD…
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
Jiho Choi, Seonho Lee, Seungho Lee +2
Open-vocabulary part segmentation (OVPS) is an emerging research area focused on segmenting fine-grained entities using diverse and previously unseen vocabularies. Our study highli…
Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
Yunji Jung, Seokju Lee, Tair Djanibekov +2
Text-guided non-rigid editing involves complex edits for input images, such as changing motion or compositions within their surroundings. Since it requires manipulating the input s…
Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
Seungho Lee, Seoungyoon Kang, Hyunjung Shim
This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweigh…
Memory-Efficient Fine-Tuning for Quantized Diffusion Model
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. However, their large-…
SeiT++: Masked Token Modeling Improves Storage-efficient Training
Minhyun Lee, Song Park, Byeongho Heo +2
Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-perfo…