http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
극소수 예시 오픈 세트 식별 문제에서의 비관측 범주 이미지 검출 성능 향상
구인용(Inyong Koo),정민기(Minki Jeong),김창익(Changick Kim) 대한전자공학회 2020 대한전자공학회 학술대회 Vol.2020 No.11
Few-shot open-set recognition is the task where a small set of support images is given, and the objective is to either classify the query images to seen classes or reject as unseen. Despite its practicality, the subject is yet less explored. In this paper, we adapt a few-shot image classification model to the open-set recognition task and suggest a better criterion for detecting unseen class images. Our method achieves better AUROC in unseen class detection without any trade-off in classification performance.
황주비(Jubi Hwang),구인용(Inyong Koo),김창익(Changick Kim) 대한전자공학회 2023 대한전자공학회 학술대회 Vol.2023 No.11
Skin cancer often goes unnoticed by patients, making early diagnosis critical to prevent metastasis. Since dermatologists play a key role in determining diagnostic accuracy, there is a growing demand for a skin cancer diagnosis assistance system to support the process of discriminating and classifying malignant tumors. Recent advancements in deep learning have shown promise in medical image recognition.However, real-world clinical data presents a long-tailed distribution, which results in biased performance toward head classes, making it difficult to be introduced at the medical site. To address these challenges, we investigate the potential of employing a contrastive visual-language model in long-tailed skin lesion recognition. Through the utilization of both the visual features extracted from images and the semantic features from the skin lesion classes, our model can successfully mitigate the biasing issue arising from data imbalance. Additionally, we evaluate whether the conventional prompt is suitable for use in medical data and design prompts that reflect the expert knowledge extracted with ChatGPT.