Zobrazeno 1 - 10
of 568
pro vyhledávání: '"HUANG, Lang"'
Open-set semi-supervised learning (OSSL) leverages practical open-set unlabeled data, comprising both in-distribution (ID) samples from seen classes and out-of-distribution (OOD) samples from unseen classes, for semi-supervised learning (SSL). Prior
Externí odkaz:
http://arxiv.org/abs/2409.17512
Image hiding is the study of techniques for covert storage and transmission, which embeds a secret image into a container image and generates stego image to make it similar in appearance to a normal image. However, existing image hiding methods have
Externí odkaz:
http://arxiv.org/abs/2407.17155
Autor:
Wu, Qiyu, Zhao, Mengjie, He, Yutong, Huang, Lang, Ono, Junya, Wakaki, Hiromi, Mitsufuji, Yuki
Reporting bias arises when people assume that some knowledge is universally understood and hence, do not necessitate explicit elaboration. In this paper, we focus on the wide existence of reporting bias in visual-language datasets, embodied as the ob
Externí odkaz:
http://arxiv.org/abs/2310.01330
Autor:
Zheng, Mingkai, You, Shan, Huang, Lang, Su, Xiu, Wang, Fei, Qian, Chen, Wang, Xiaogang, Xu, Chang
Image classification is a longstanding problem in computer vision and machine learning research. Most recent works (e.g. SupCon , Triplet, and max-margin) mainly focus on grouping the intra-class samples aggressively and compactly, with the assumptio
Externí odkaz:
http://arxiv.org/abs/2308.10761
Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor. In this paper, we introduce a new semi-supervised learning algorithm - SimMatchV2, which formulates
Externí odkaz:
http://arxiv.org/abs/2308.06692
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to convolutions as a plug-and-play module and embed them in various ViT co
Externí odkaz:
http://arxiv.org/abs/2207.05557
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate only on the visible ones. Our approach consists of three key designs.
Externí odkaz:
http://arxiv.org/abs/2205.13515
Self-supervised learning (SSL) has made enormous progress and largely narrowed the gap with the supervised ones, where the representation learning is mainly guided by a projection into an embedding space. During the projection, current methods simply
Externí odkaz:
http://arxiv.org/abs/2203.14898
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community. In this paper, we introduced a new semi-supervised learning framework, SimMatch, which simultaneously considers semantic si
Externí odkaz:
http://arxiv.org/abs/2203.06915
Autor:
Huang, Lang1 (AUTHOR) m17362493690@163.com, Liu, Yarong1 (AUTHOR) treasuremark@163.com, Guan, Zhipeng1,2 (AUTHOR) 23071108@wit.edu.cn, Dong, Zhibing1,2,3 (AUTHOR) 23071108@wit.edu.cn
Publikováno v:
Catalysts (2073-4344). Sep2024, Vol. 14 Issue 9, p601. 11p.
