We live in a vast ocean of data, and deep neural networks are no exception to this. However,
this data exhibits an inherent phenomenon of imbalance. This imbalance poses a risk of …

Bias mitigation in image classification has been widely researched, and existing methods
have yielded notable results. However, most of these methods implicitly assume that a given …

In the image classification task deep neural networks frequently rely on bias attributes that
are spuriously correlated with a target class in the presence of dataset bias resulting in …

Mixup is a highly successful technique to improve generalization of neural networks by
augmenting the training data with combinations of random pairs. Selective mixup is a family …

Recent studies have noted an intriguing phenomenon termed Neural Collapse that is when
the neural networks establish the right correlation between feature spaces and the training …

Data augmentation is an essential building block for learning efficient deep learning models.
Among all augmentation techniques proposed so far, linear interpolation of training data …

Dataset Condensation has emerged as a technique for compressing large datasets into
smaller synthetic counterparts, facilitating downstream training tasks. In this paper, we study …

Predicting future trajectories for other road agents is an essential task for autonomous
vehicles. Established trajectory prediction methods primarily use agent tracks generated by …

The rise in internet usage has led to the generation of massive amounts of data, resulting in
the adoption of various supervised and semi-supervised machine learning algorithms, which …

Spurious correlations in training data significantly hinder the generalization capability of
machine learning models when faced with distribution shifts in real-world scenarios. To …