Výsledky vyhledávání - "Yun, JungMin"

Report

DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation

Autor: Jang, Soojin, Yun, Jungmin, Kwon, Junehyoung, Lee, Eunju, 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

Zobrazit plný text záznamu

Report

VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks

Autor: Choi, Juhwan, Kwon, Junehyoung, Yun, JungMin, Yu, Seunguk, Kim, YoungBin

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

Zobrazit plný text záznamu

Report

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification

Autor: Yun, Jungmin, Kim, Mihyeon, Kim, Youngbin

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

Zobrazit plný text záznamu

Report

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation

Autor: Choi, Juhwan, Kim, Yeonghwa, Yu, Seunguk, Yun, JungMin, Kim, YoungBin

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

Zobrazit plný text záznamu

Report

Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation

Autor: Choi, Juhwan, Yun, Jungmin, Jin, Kyohoon, Kim, YoungBin

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

Zobrazit plný text záznamu