Zobrazeno 1 - 10
of 165
pro vyhledávání: '"Kim, YoungBin"'
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address this issue
Externí odkaz:
http://arxiv.org/abs/2409.15801
Autor:
Choi, Juhwan, Kim, YoungBin
Large language models (LLMs) have become a dominant approach in natural language processing, yet their internal knowledge structures remain largely unexplored. In this paper, we analyze the internal knowledge structures of LLMs using historical medal
Externí odkaz:
http://arxiv.org/abs/2409.06518
In this work, we present a quantum theory for pulsed photon pair generation in a single ring resonator. Our approach combines the Heisenberg picture input-output formalism with the Ikeda mapping from classical nonlinear optics. In doing so, we addres
Externí odkaz:
http://arxiv.org/abs/2408.10776
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research on the domain generalizability of deep learning models for vision-lang
Externí odkaz:
http://arxiv.org/abs/2407.19795
Autor:
Kim, Youngbin
As cardiovascular disease remains the global leading cause of death, there is an urgent need to study the pathophysiology of the heart and to effectively evaluate cardioprotective drugs. Due to the difficulty in studying the human heart in vivo and s
Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts with all toke
Externí odkaz:
http://arxiv.org/abs/2406.01283
Weakly supervised semantic segmentation (WSSS) employing weak forms of labels has been actively studied to alleviate the annotation cost of acquiring pixel-level labels. However, classifiers trained on biased datasets tend to exploit shortcut feature
Externí odkaz:
http://arxiv.org/abs/2405.18148
Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference. Recent studies have suggested that PLMs
Externí odkaz:
http://arxiv.org/abs/2405.01022
The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models. However, datasets often contain noisy data inadvertently included during the construction process. Numerous attempts have been made to c
Externí odkaz:
http://arxiv.org/abs/2404.09682
Autor:
Choi, Juhwan, Kim, YoungBin
In the field of text data augmentation, rule-based methods are widely adopted for real-world applications owing to their cost-efficiency. However, conventional rule-based approaches suffer from the possibility of losing the original semantics of the
Externí odkaz:
http://arxiv.org/abs/2403.20015