Zobrazeno 1 - 10
of 553
pro vyhledávání: '"Lee, Dong-Gyu"'
This paper introduces a method for VizWiz-VQA using LVLM with trainable cross-attention and LoRA finetuning. We train the model with the following conditions: 1) Training with original images. 2) Training with enhanced images using CLIPSeg to highlig
Externí odkaz:
http://arxiv.org/abs/2407.12055
Autor:
Kumar, Abhishek, Lee, Dong-Gyu
Contemporary deep clustering approaches often rely on either contrastive or non-contrastive techniques to acquire effective representations for clustering tasks. Contrastive methods leverage negative pairs to achieve homogenous representations but ca
Externí odkaz:
http://arxiv.org/abs/2311.00731
The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated annotations.
Externí odkaz:
http://arxiv.org/abs/2310.07149
Remotely captured images possess an immense scale and object appearance variability due to the complex scene. It becomes challenging to capture the underlying attributes in the global and local context for their segmentation. Existing networks strugg
Externí odkaz:
http://arxiv.org/abs/2302.13084
Convolutional Neural Networks (CNNs) have a large number of parameters and take significantly large hardware resources to compute, so edge devices struggle to run high-level networks. This paper proposes a novel method to reduce the parameters and FL
Externí odkaz:
http://arxiv.org/abs/2301.11063
Autor:
Su, Xukun, Xu, Junjie, Chen, Xiaoyu, Sun, Shuailing, Lee, Dong-Gyu, Zhu, Beining, Baik, Jeong Min, Hur, SungHoon, Fan, Shengbo, Song, Hyun-Cheol, Leng, Yonggang
Publikováno v:
In Nano Energy 1 June 2024 124
Publikováno v:
In Applied Soft Computing April 2024 155
Publikováno v:
In Expert Systems With Applications 15 March 2024 238 Part E
Publikováno v:
In Swarm and Evolutionary Computation February 2024 84
Visual question answering requires a deep understanding of both images and natural language. However, most methods mainly focus on visual concept; such as the relationships between various objects. The limited use of object categories combined with t
Externí odkaz:
http://arxiv.org/abs/2101.08978