Recent advancements in autonomous driving, augmented reality, robotics, and embodied
intelligence have necessitated 3D perception algorithms. However, current 3D perception …

In real-world scenarios, the number of training samples across classes usually subjects to a
long-tailed distribution. The conventionally trained network may achieve unexpected inferior …

Traditional methods for object detection typically necessitate a substantial amount of training
data, and creating high-quality training data is time-consuming. We propose a novel Few …

Few-shot object detection (FSOD) has garnered widespread attention in recent years, which
makes it possible to learn novel classes with only a handful of labeled samples. Due to the …

Logit adjustment is an effective long-tailed visual recognition strategy to encourage a
significant margin between rare and dominant labels. Existing methods typically employ the …

Recent years have witnessed tremendous advances on modern visual recognition systems.
Despite such progress, many vision models still struggle with the open problem of learning …

Real-world data coming from settings like hospital collections for detecting disease
experience multiple sources of distributional shifts. These issues affect the performance of …