Related papers: Towards Interpreting and Mitigating Shortcut Learn…

Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training…

End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…

Long-tail distribution is widely spread in real-world applications. Due to the extremely small ratio of instances, tail categories often show inferior accuracy. In this paper, we find such performance bottleneck is mainly caused by the…

Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition. However, the long-tailed data distribution can corrupt the representation space, where the distance…

Long-tailed data is a special type of multi-class imbalanced data with a very large amount of minority/tail classes that have a very significant combined influence. Long-tailed learning aims to build high-performance models on datasets with…

In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of…

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…

We study the classification of animal behavior using accelerometry data through various recurrent neural network (RNN) models. We evaluate the classification performance and complexity of the considered models, which feature long short-time…

Transformer-based models have achieved remarkable success in various Natural Language Processing (NLP) tasks, yet their ability to handle long documents is constrained by computational limitations. Traditional approaches, such as truncating…

Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a…

It has been shown that instead of learning actual object features, deep networks tend to exploit non-robust (spurious) discriminative features that are shared between training and test sets. Therefore, while they achieve state of the art…

The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly determined by the average loss assessed on a testing set,…

A unique feature of Recurrent Neural Networks (RNNs) is that it incrementally processes input sequences. In this research, we aim to uncover the inherent generalization properties, i.e., inductive bias, of RNNs with respect to how…

Empirical Risk Minimization (ERM) models often rely on spurious correlations between features and labels during the learning process, leading to shortcut learning behavior that undermines robustness generalization performance. Current…

Natural language understanding (NLU) is the task of semantic decoding of human languages by machines. NLU models rely heavily on large training data to ensure good performance. However, substantial languages and domains have very few data…

In graph classification, attention and pooling-based graph neural networks (GNNs) prevail to extract the critical features from the input graph and support the prediction. They mostly follow the paradigm of learning to attend, which…

We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks. Different from the softmax cross-entropy loss, our proposal is established on the assumption that the deep features of the training set…

In English and other languages, multiple adjectives in noun phrases follow intricate ordering patterns. These patterns have been widely studied in linguistics and provide a useful test case for assessing how language models (LMs) acquire…