Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Choi, Seokeon"'
Autor:
Cho, Wonguk, Choi, Seokeon, Das, Debasmit, Reisser, Matthias, Kim, Taesup, Yun, Sungrack, Porikli, Fatih
Recent advancements in text-to-image diffusion models have enabled the personalization of these models to generate custom images from textual prompts. This paper presents an efficient LoRA-based personalization approach for on-device subject-driven g
Externí odkaz:
http://arxiv.org/abs/2411.01179
Federated learning, a distributed learning paradigm, utilizes multiple clients to build a robust global model. In real-world applications, local clients often operate within their limited domains, leading to a `domain shift' across clients. Privacy c
Externí odkaz:
http://arxiv.org/abs/2407.08245
Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random Convolutions (RandConv), consisting of one convolution layer randomly
Externí odkaz:
http://arxiv.org/abs/2304.00424
This paper proposes a novel test-time adaptation strategy that adjusts the model pre-trained on the source domain using only unlabeled online data from the target domain to alleviate the performance degradation due to the distribution shift between t
Externí odkaz:
http://arxiv.org/abs/2207.11707
Autor:
Lee, Sumin, Eun, Hyunjun, Moon, Jinyoung, Choi, Seokeon, Kim, Yoonhyung, Jung, Chanho, Kim, Changick
Online action detection, which aims to identify an ongoing action from a streaming video, is an important subject in real-world applications. For this task, previous methods use recurrent neural networks for modeling temporal relations in an input se
Externí odkaz:
http://arxiv.org/abs/2109.03393
In this paper, we attack a few-shot open-set recognition (FSOSR) problem, which is a combination of few-shot learning (FSL) and open-set recognition (OSR). It aims to quickly adapt a model to a given small set of labeled samples while rejecting unsee
Externí odkaz:
http://arxiv.org/abs/2103.01537
Although supervised person re-identification (Re-ID) methods have shown impressive performance, they suffer from a poor generalization capability on unseen domains. Therefore, generalizable Re-ID has recently attracted growing attention. Many existin
Externí odkaz:
http://arxiv.org/abs/2011.14670
We propose an improved discriminative model prediction method for robust long-term tracking based on a pre-trained short-term tracker. The baseline pre-trained short-term tracker is SuperDiMP which combines the bounding-box regressor of PrDiMP with t
Externí odkaz:
http://arxiv.org/abs/2008.04722
Visible-infrared person re-identification (VI-ReID) is an important task in night-time surveillance applications, since visible cameras are difficult to capture valid appearance information under poor illumination conditions. Compared to traditional
Externí odkaz:
http://arxiv.org/abs/1912.01230
In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data.Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture that matches pixels between adjacent f
Externí odkaz:
http://arxiv.org/abs/1909.13247