Prevalent federated learning commonly develops under the assumption that the ideal global
class distributions are balanced. In contrast, real-world data typically follows the long-tailed …

Extensive advancements have been made in person ReID through the mining of semantic
information. Nevertheless existing methods that utilize semantic-parts from a single image …

Data mixing methods play a crucial role in semi-supervised learning (SSL) but their
application is unexplored in long-tailed semi-supervised learning (LTSSL). The primary …

Recent long-tailed classification methods generally adopt the two-stage pipeline and focus
on learning the classifier to tackle the imbalanced data in the second stage via re-sampling …

Recent expert ensemble methods for long-tailed recognition encourage diversity by
maximizing KL divergence between the predictions of experts. However, the excessive …

The activation function plays a crucial role in model optimisation, yet the optimal choice
remains unclear. For example, the Sigmoid activation is the de-facto activation in balanced …

Existing continual learning literature relies heavily on a strong assumption that tasks arrive
with a balanced data stream, which is often unrealistic in real-world applications. In this …

Despite the availability of large datasets for tasks like image classification and image-text
alignment, labeled data for more complex recognition tasks, such as detection and …

In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated
remarkable capabilities among various methods. This paradigm decouples the training …

federated learning has been introduced into person re-identification (Re-ID) to avoid
personal image leakage in traditional centralized training. To address the key issue of …