An Efficient Noisy Label Learning Method with Semi-supervised Learning

Kim, Jihee; Park, Gwan Soo; Roh, Si-Dong; Chung, Ki-Seok

doi:10.1145/3589572.3589596

Cited by 1 publication

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Scaling up a dataset for pretraining has advanced in deep learning communities while suggesting a new horizon for zero-shot and few-shot transfer. The recent success of pretrained language models, such as bidirectional encoder representations from transformers (BERT; Devlin et al, 2018) and generative pretrained transformer (GPT) series (Brown et al, 2020;Radford et al, 2018Radford et al, , 2019, inspired researchers to extend these models to perform visionrelated tasks (Chen et al, 2020;Kim et al, 2021;L. H. Li et al, 2019;X.…”

Section: Clipmentioning

confidence: 99%

Prompt engineering for zero‐shot and few‐shot defect detection and classification using a visual‐language pretrained model

Yong

Jeon

Gil

et al. 2022

Computer aided Civil Eng

View full text Add to dashboard Cite

Zero‐shot learning, applied with vision‐language pretrained (VLP) models, is expected to be an alternative to existing deep learning models for defect detection, under insufficient dataset. However, VLP models, including contrastive language‐image pretraining (CLIP), showed fluctuated performance on prompts (inputs), resulting in research on prompt engineering—optimization of prompts for improving performance. Therefore, this study aims to identify the features of a prompt that can yield the best performance in classifying and detecting building defects using the zero‐shot and few‐shot capabilities of CLIP. The results reveal the following: (1) domain‐specific definitions are better than general definitions and images; (2) a complete sentence is better than a set of core terms; and (3) multimodal information is better than single‐modal information. The resulting detection performance using the proposed prompting method outperformed that of existing supervised models.

show abstract