Zobrazeno 1 - 10
of 188
pro vyhledávání: '"Chun, Se Young"'
Generating higher-resolution human-centric scenes with details and controls remains a challenge for existing text-to-image diffusion models. This challenge stems from limited training image size, text encoder capacity (limited tokens), and the inhere
Externí odkaz:
http://arxiv.org/abs/2404.04544
Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire data from the past, present as well as future is considered as the gold s
Externí odkaz:
http://arxiv.org/abs/2312.13027
Deep learning, in general, focuses on training a neural network from large labeled datasets. Yet, in many cases there is value in training a network just from the input at hand. This is particularly relevant in many signal and image processing proble
Externí odkaz:
http://arxiv.org/abs/2312.07425
Autor:
Lee, Haechang, Jeong, Wongi, Ryu, Dongil, Je, Hyunwoo, No, Albert, Kim, Kijeong, Chun, Se Young
Despite significant research on lightweight deep neural networks (DNNs) designed for edge devices, the current face detectors do not fully meet the requirements for "intelligent" CMOS image sensors (iCISs) integrated with embedded DNNs. These sensors
Externí odkaz:
http://arxiv.org/abs/2311.01001
Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or without smal
Externí odkaz:
http://arxiv.org/abs/2308.14374
Autor:
Lee, Haechang, Park, Dongwon, Jeong, Wongi, Kim, Kijeong, Je, Hyunwoo, Ryu, Dongil, Chun, Se Young
As the physical size of recent CMOS image sensors (CIS) gets smaller, the latest mobile cameras are adopting unique non-Bayer color filter array (CFA) patterns (e.g., Quad, Nona, QxQ), which consist of homogeneous color units with adjacent pixels. Th
Externí odkaz:
http://arxiv.org/abs/2307.10667
Autor:
Hong, Seongmin, Chun, Se Young
Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibility. For instance, the computat
Externí odkaz:
http://arxiv.org/abs/2304.04555
The increasing demand for high-quality 3D content creation has motivated the development of automated methods for creating 3D object models from a single image and/or from a text prompt. However, the reconstructed 3D objects using state-of-the-art im
Externí odkaz:
http://arxiv.org/abs/2304.02827
Recently, significant advancements have been made in 3D generative models, however training these models across diverse domains is challenging and requires an huge amount of training data and knowledge of pose distribution. Text-guided domain adaptat
Externí odkaz:
http://arxiv.org/abs/2304.01900
Conditional normalizing flows can generate diverse image samples for solving inverse problems. Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse images quickly. However, unin
Externí odkaz:
http://arxiv.org/abs/2212.04319