S Wen, M Brbic - arXiv preprint arXiv:2406.11422, 2024 - arxiv.org
In many real-world applications, test data may commonly exhibit categorical shifts, characterized by the emergence of novel classes, as well as distribution shifts arising from …
M Grcić, A Gadetsky, M Brbić - arXiv preprint arXiv:2406.11070, 2024 - arxiv.org
In many practical applications, coarse-grained labels are readily available compared to fine- grained labels that reflect subtle differences between classes. However, existing methods …
In many practical applications, coarse-grained labels are readily available compared to fine- grained labels that reflect subtle differences between classes. However, existing methods …
Recent self-supervised learning methods, where instance discrimination is a fundamental pretraining task for convolutional neural networks (CNNs), excel in transfer learning. While …