Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Kim, Jaeill"'
The latest advancements in unsupervised learning of sentence embeddings predominantly involve employing contrastive learning-based (CL-based) fine-tuning over pre-trained language models. In this study, we analyze the latest sentence embedding method
Externí odkaz:
http://arxiv.org/abs/2405.11297
Class Incremental Learning (CIL) constitutes a pivotal subfield within continual learning, aimed at enabling models to progressively learn new classification tasks while retaining knowledge obtained from prior tasks. Although previous studies have pr
Externí odkaz:
http://arxiv.org/abs/2403.15517
In the past few years, contrastive learning has played a central role for the success of visual unsupervised representation learning. Around the same time, high-performance non-contrastive learning methods have been developed as well. While most of t
Externí odkaz:
http://arxiv.org/abs/2401.05730
Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with a mutual information loss. The loss is known as InfoNCE and it has yi
Externí odkaz:
http://arxiv.org/abs/2308.15704
Since the introduction of deep learning, a wide scope of representation properties, such as decorrelation, whitening, disentanglement, rank, isotropy, and mutual information, have been studied to improve the quality of representation. However, manipu
Externí odkaz:
http://arxiv.org/abs/2304.01434
In autonomous driving, data augmentation is commonly used for improving 3D object detection. The most basic methods include insertion of copied objects and rotation and scaling of the entire training frame. Numerous variants have been developed as we
Externí odkaz:
http://arxiv.org/abs/2303.12743
Publikováno v:
In Neural Networks November 2024 179