Object detection is a crucial branch of computer vision that aims to locate and classify
objects in images. Using deep convolutional neural networks (CNNs) as the primary …

The grid-centric perception is a crucial field for mobile robot perception and navigation.
Nonetheless, the grid-centric perception is less prevalent than object-centric perception as …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

In the field of visual scene understanding, deep neural networks have made impressive
advancements in various core tasks like segmentation, tracking, and detection. However …

Object models are gradually progressing from predicting just category labels to providing
detailed descriptions of object instances. This motivates the need for large datasets which …

Detecting out-of-distribution (OOD) objects is indispensable for safely deploying object
detectors in the wild. Although distance-based OOD detection methods have demonstrated …

Abstract Open World Object Detection (OWOD) is a new and challenging computer vision
task that bridges the gap between classic object detection (OD) benchmarks and object …

In this paper, we study the problem of unsupervised object detection from 3D point clouds in
self-driving scenes. We present a simple yet effective method that exploits (i) point clustering …

Benefiting from large-scale vision-language pre-training on image-text pairs, open-world
detection methods have shown superior generalization ability under the zero-shot or few …

In incremental learning, replaying stored samples from previous tasks together with current
task samples is one of the most efficient approaches to address catastrophic forgetting …