Image Classification
Empirical risk minimization (ERM) is sensitive to spurious correlations present in training data, which poses a significant risk when …
A well-known failure mode of neural networks is that they may confidently return erroneous predictions. Such unsafe behaviour is …
Transfer learning from large-scale pre-trained models has become essential for many computer vision tasks. Recent studies have shown …
Remote sensing and automatic earth monitoring are key to solve global-scale challenges such as disaster prevention, land use …
Data augmentation is a key practice in machine learning for improving generalization performance. However, finding the best data …
Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as …
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly …
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric …
Fine-grained image recognition is central to many multimedia tasks such as search, retrieval and captioning. Unfortunately, these tasks …