3 papers
cs.LG2026
The Impact of Semantic Pairs on Self-Supervised Representation Learning
Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this encourages invariance to handcrafted tra…
cs.CV2025
Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methods
Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results, performing competitively or even outperforming supervised learning counterp…
cs.CV2025
LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavil…