The feature generator of hard negative samples for fine-grained image recognition
Sign Up to like & getrecommendations! Published in 2021 at "Neurocomputing"
DOI: 10.1016/j.neucom.2020.10.032
Abstract: Abstract The key to solving the fine-grained image recognition is exploring more discriminative features for capturing tiny hints. In particular, the triplet objective function fits well with the fine-grained image recognition task because they capture… read more here.
Keywords: fine grained; grained image; image recognition; negative samples ... See more keywords
The relationship between poor CSR performance and hard, negative CSR information disclosures
Sign Up to like & getrecommendations! Published in 2020 at "Sustainability Accounting, Management and Policy Journal"
DOI: 10.1108/sampj-04-2020-0094
Abstract: The purpose of this paper is to investigate the relationship between hard, negative corporate social responsibility (CSR) information disclosure and corporate social performance.,This study uses a generalised least squares panel data analysis based on a… read more here.
Keywords: negative csr; csr information; performance; hard negative ... See more keywords
Multisource Soft Labeling and Hard Negative Sampling for Retrieval Distractor Ranking
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Learning Technologies"
DOI: 10.1109/tlt.2023.3325549
Abstract: Multiple-choice questions (MCQs) are a kind of widely adopted approaches in learning assessment. Recently, the automatic generation of MCQs has become a popular research area. In this task, distractor ranking (DR) is one of the… read more here.
Keywords: multisource soft; distractor ranking; retrieval distractor; hard negative ... See more keywords
Lesion-Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Medical Imaging"
DOI: 10.1109/tmi.2020.3022034
Abstract: The acquisition of large-scale medical image data, necessary for training machine learning algorithms, is hampered by associated expert-driven annotation costs. Mining hospital archives can address this problem, but labels often incomplete or noisy, e.g., 50%… read more here.
Keywords: lesion harvester; deeplesion; hard negative; harvester iteratively ... See more keywords