Results 1 to 10 of about 115,093 (312)
Contrastive learning and neural oscillations [PDF]
Neural Computation, 1991 The concept of Contrastive Learning (CL) is developed as a family of possible learning algorithms for neural networks. CL is an extension of Deterministic Boltzmann Machines to more general dynamical systems.
Baldi, Pierre, Pineda, Fernando
core +5 more sources
Parametric Contrastive Learning [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes and thus increases the difficulty of imbalanced learning.
Cui, Jiequan +4 more
openaire +2 more sources
Applied Sciences, 2023 Font is a crucial design aspect, however, classifying fonts is challenging compared with that of other natural objects, as fonts differ from images. This paper presents the application of contrastive learning in font style classification.
Irfanullah Memon +2 more
doaj +1 more source
Clustering of Short Texts Based on Dynamic Adjustment for Contrastive Learning
IEEE Access, 2022 Faced with the large amount of unlabeled short text data appearing on the Internet, it is necessary to categorize them using clustering that can divide text into several clusters based on similarity degree of text semantics.
Ruihui Li, Hongbin Wang
doaj +1 more source
Universum-Inspired Supervised Contrastive Learning
IEEE Transactions on Image Processing, 2023 As an effective data augmentation method, Mixup synthesizes an extra amount of samples through linear interpolations. Despite its theoretical dependency on data properties, Mixup reportedly performs well as a regularizer and calibrator contributing reliable robustness and generalization to deep model training.
Aiyang Han, Chuanxing Geng, Songcan Chen
openaire +3 more sources
CL-TAD: A Contrastive-Learning-Based Method for Time Series Anomaly Detection
Applied Sciences, 2023 Anomaly detection has gained increasing attention in recent years, but detecting anomalies in time series data remains challenging due to temporal dynamics, label scarcity, and data diversity in real-world applications.
Huynh Cong Viet Ngu, Keon Myung Lee
doaj +1 more source
Contrastive Representation Learning: A Framework and Review
IEEE Access, 2020 Contrastive Learning has recently received interest due to its success in self-supervised representation learning in the computer vision domain. However, the origins of Contrastive Learning date as far back as the 1990s and its development has spanned ...
Phuc H. Le-Khac +2 more
doaj +1 more source
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
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