Optimizing Contrastive Learning with Semi-Online Triplet Mining
Contrastive learning is a machine learning technique in which models learn by contrasting similar and dissimilar data points. Its goal is to learn a representation of data in such a way that similar instances are close together in the representation space, while dissimilar instances are far apart. O...
Saved in:
| Main Authors: | Przemysław Buczkowski, Marek Kozłowski, Piotr Brzeziński |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7865 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Optimizing Pre-Trained Code Embeddings With Triplet Loss for Code Smell Detection
by: Ali Nizam, et al.
Published: (2025-01-01) -
Semiconductor nanocrystals‐based triplet‐triplet annihilation photon‐upconversion: Mechanism, materials and applications
by: Kezhou Chen, et al.
Published: (2025-02-01) -
Confinement‐Enhanced Multi‐Wavelength Photon Upconversion Based on Triplet–Triplet Annihilation in Nanostructured Glassy Polymers
by: Xueqian Hu, et al.
Published: (2025-04-01) -
ACtriplet: An improved deep learning model for activity cliffs prediction by in tegrating triplet loss and pre-training
by: Xinxin Yu, et al.
Published: (2025-08-01) -
TripletA-Net: A Deep Learning Model for Automatic Railway Track Extraction from Airborne LiDAR Point Clouds
by: Runyuan Zhang, et al.
Published: (2025-01-01)