Existing vision-text contrastive learning like CLIP aims to match the paired image and
caption embeddings while pushing others apart, which improves representation …

Subsampling focuses on selecting a subsample that can efficiently sketch the information of
the original data in terms of statistical inference. It provides a powerful tool in big data …

Data are invaluable. How can we assess the value of data objectively, systematically and
quantitatively? Pricing data, or information goods in general, has been studied and practiced …

Quantifying the value of data is a fundamental problem in machine learning and has multiple
important use cases:(1) building insights about the dataset and task,(2) domain …

Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

The performance of supervised learning methods easily suffers from the training bias issue
caused by train-test distribution mismatch or label noise. Influence function is a technique …

Continual learning aims to learn on non-stationary data streams without catastrophically
forgetting previous knowledge. Prevalent replay-based methods address this challenge by …

Large-scale datasets have played a crucial role in the advancement of computer vision.
However, they often suffer from problems such as class imbalance, noisy labels, dataset …

Through a deeper understanding of predictions of neural networks, Influence Function (IF)
has been applied to various tasks such as detecting and relabeling mislabeled samples …

Influence function, a method from robust statistics, measures the changes of model
parameters or some functions about model parameters concerning the removal or …