The ability to detect aerial objects with limited annotation is pivotal to the development of real-world aerial intelligence systems. In this work, we focus on a demanding but practical sparsely annotated object detection (SAOD) in aerial images, which encompasses a wider variety of aerial scenes with the same number of annotated objects.

In online learning, a decision maker repeatedly selects one of a set of actions, with the goal of minimizing the overall loss incurred.

The rapid development of large language and vision models (LL VMs) has been driven by advances in visual instruction tuning.

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of

We show how this idealized loss can be reformulated to a functionally equivalent loss that is more efficient to compute.

In contrast to previous work on this learning model, we consider scenarios in which the family of groups is too large to explicitly enumerate, and hence we seek algorithms that only access groups via an optimization oracle.

Test-time adaptation (TT A) is the most realistic methodology for adapting deep learning models to the real world using only unlabeled data from the target domain. Numerous TT A studies in deep learning have aimed at minimizing entropy. However, this necessitates forward/backward processes across the entire model and is limited by the incapability to fully leverage data based solely on entropy.

Pre-trained large language models (LLMs) based on Transformer have demonstrated striking in-context learning (ICL) abilities.