Results 21 to 30 of about 14,201 (266)
What Should Not Be Contrastive in Contrastive Learning
CoRR, 2020 Published as a conference paper at ICLR ...
Tete Xiao +3 more
openaire +3 more sources
An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
Entropy, 2022 Contrastive learning is a representation learning method performed by contrasting a sample to other similar samples so that they are brought closely together, forming clusters in the feature space.
Valentino Vito, Lim Yohanes Stefanus
doaj +1 more source
Equivariant Contrastive Learning
CoRR, 2021 In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the ...
Rumen Dangovski +7 more
openaire +2 more sources
SelfCCL: Curriculum Contrastive Learning by Transferring Self-Taught Knowledge for Fine-Tuning BERT
Applied Sciences, 2023 BERT, the most popular deep learning language model, has yielded breakthrough results in various NLP tasks. However, the semantic representation space learned by BERT has the property of anisotropy.
Somaiyeh Dehghan, Mehmet Fatih Amasyali
doaj +1 more source
Decoupled Contrastive Learning
, 2022 Contrastive learning (CL) is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented "views" of the same image as positive to be pulled closer, and all other images as negative to be pushed further apart.
Chun-Hsiao Yeh +5 more
openaire +2 more sources
Al-Takhlil al-Taqabuly fi Ta'lim al-Lughah al-'Arabiyyah
Jurnal Al Bayan: Jurnal Jurusan Pendidikan Bahasa Arab, 2020 This article explains systematically the nature of contrastive analysis in language learning. Throughout this article the writer investigates the development of contrastive analysis in the field of language learning, its main objectives, some hypotheses ...
Ahmad Bukhari Muslim
doaj +1 more source
Grouped Contrastive Learning of Self-Supervised Sentence Representation
Applied Sciences, 2023 This paper proposes a method called Grouped Contrastive Learning of self-supervised Sentence Representation (GCLSR), which can learn an effective and meaningful representation of sentences. Previous works maximize the similarity between two vectors to be
Qian Wang +3 more
doaj +1 more source
Supervised Contrastive Learning
CoRR, 2020 Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches subsume or significantly outperform traditional contrastive losses such as triplet, max-margin and the N-pairs loss.
Prannay Khosla +8 more
openaire +3 more sources
A Contrastive Rule for Meta-Learning
Advances in Neural Information Processing Systems 35, 2022 Meta-learning algorithms leverage regularities that are present on a set of tasks to speed up and improve the performance of a subsidiary learning process. Recent work on deep neural networks has shown that prior gradient-based learning of meta-parameters can greatly improve the efficiency of subsequent learning.
Zucchet, Nicolas +4 more
openaire +4 more sources
CoRR, 2020 A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled datapoints, implicitly accepting that these points may, in reality, actually have the same label.
Ching-Yao Chuang +4 more
openaire +3 more sources